Daily Papers

We propose to address quadrupedal locomotion tasks using Reinforcement Learning (RL) with a Transformer-based model that learns to combine proprioceptive information and high-dimensional depth sensor inputs. While learning-based locomotion has made great advances using RL, most methods still rely on domain randomization for training blind agents that generalize to challenging terrains. Our key insight is that proprioceptive states only offer contact measurements for immediate reaction, whereas an agent equipped with visual sensory observations can learn to proactively maneuver environments with obstacles and uneven terrain by anticipating changes in the environment many steps ahead. In this paper, we introduce LocoTransformer, an end-to-end RL method that leverages both proprioceptive states and visual observations for locomotion control. We evaluate our method in challenging simulated environments with different obstacles and uneven terrain. We transfer our learned policy from simulation to a real robot by running it indoors and in the wild with unseen obstacles and terrain. Our method not only significantly improves over baselines, but also achieves far better generalization performance, especially when transferred to the real robot. Our project page with videos is at https://rchalyang.github.io/LocoTransformer/ .

In this technical report, we introduce our solution to human-centric spatio-temporal video grounding task. We propose a concise and effective framework named STVGFormer, which models spatiotemporal visual-linguistic dependencies with a static branch and a dynamic branch. The static branch performs cross-modal understanding in a single frame and learns to localize the target object spatially according to intra-frame visual cues like object appearances. The dynamic branch performs cross-modal understanding across multiple frames. It learns to predict the starting and ending time of the target moment according to dynamic visual cues like motions. Both the static and dynamic branches are designed as cross-modal transformers. We further design a novel static-dynamic interaction block to enable the static and dynamic branches to transfer useful and complementary information from each other, which is shown to be effective to improve the prediction on hard cases. Our proposed method achieved 39.6% vIoU and won the first place in the HC-STVG track of the 4th Person in Context Challenge.

The success of deep learning heavily relies on large-scale data with comprehensive labels, which is more expensive and time-consuming to fetch in 3D compared to 2D images or natural languages. This promotes the potential of utilizing models pretrained with data more than 3D as teachers for cross-modal knowledge transferring. In this paper, we revisit masked modeling in a unified fashion of knowledge distillation, and we show that foundational Transformers pretrained with 2D images or natural languages can help self-supervised 3D representation learning through training Autoencoders as Cross-Modal Teachers (ACT). The pretrained Transformers are transferred as cross-modal 3D teachers using discrete variational autoencoding self-supervision, during which the Transformers are frozen with prompt tuning for better knowledge inheritance. The latent features encoded by the 3D teachers are used as the target of masked point modeling, wherein the dark knowledge is distilled to the 3D Transformer students as foundational geometry understanding. Our ACT pretrained 3D learner achieves state-of-the-art generalization capacity across various downstream benchmarks, e.g., 88.21% overall accuracy on ScanObjectNN. Codes have been released at https://github.com/RunpeiDong/ACT.

Scene understanding based on image segmentation is a crucial component of autonomous vehicles. Pixel-wise semantic segmentation of RGB images can be advanced by exploiting complementary features from the supplementary modality (X-modality). However, covering a wide variety of sensors with a modality-agnostic model remains an unresolved problem due to variations in sensor characteristics among different modalities. Unlike previous modality-specific methods, in this work, we propose a unified fusion framework, CMX, for RGB-X semantic segmentation. To generalize well across different modalities, that often include supplements as well as uncertainties, a unified cross-modal interaction is crucial for modality fusion. Specifically, we design a Cross-Modal Feature Rectification Module (CM-FRM) to calibrate bi-modal features by leveraging the features from one modality to rectify the features of the other modality. With rectified feature pairs, we deploy a Feature Fusion Module (FFM) to perform sufficient exchange of long-range contexts before mixing. To verify CMX, for the first time, we unify five modalities complementary to RGB, i.e., depth, thermal, polarization, event, and LiDAR. Extensive experiments show that CMX generalizes well to diverse multi-modal fusion, achieving state-of-the-art performances on five RGB-Depth benchmarks, as well as RGB-Thermal, RGB-Polarization, and RGB-LiDAR datasets. Besides, to investigate the generalizability to dense-sparse data fusion, we establish an RGB-Event semantic segmentation benchmark based on the EventScape dataset, on which CMX sets the new state-of-the-art. The source code of CMX is publicly available at https://github.com/huaaaliu/RGBX_Semantic_Segmentation.

In this paper, we re-examine the task of cross-modal clip-sentence retrieval, where the clip is part of a longer untrimmed video. When the clip is short or visually ambiguous, knowledge of its local temporal context (i.e. surrounding video segments) can be used to improve the retrieval performance. We propose Context Transformer (ConTra); an encoder architecture that models the interaction between a video clip and its local temporal context in order to enhance its embedded representations. Importantly, we supervise the context transformer using contrastive losses in the cross-modal embedding space. We explore context transformers for video and text modalities. Results consistently demonstrate improved performance on three datasets: YouCook2, EPIC-KITCHENS and a clip-sentence version of ActivityNet Captions. Exhaustive ablation studies and context analysis show the efficacy of the proposed method.

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move a step forward and design an approach that allows for multimodal queries, composed of both an image and a text, and can search within collections of multimodal documents, where images and text are interleaved. Our model, ReT, employs multi-level representations extracted from different layers of both visual and textual backbones, both at the query and document side. To allow for multi-level and cross-modal understanding and feature extraction, ReT employs a novel Transformer-based recurrent cell that integrates both textual and visual features at different layers, and leverages sigmoidal gates inspired by the classical design of LSTMs. Extensive experiments on M2KR and M-BEIR benchmarks show that ReT achieves state-of-the-art performance across diverse settings. Our source code and trained models are publicly available at https://github.com/aimagelab/ReT.

Although deep learning models have had great success in natural language processing and computer vision, we do not observe comparable improvements in the case of tabular data, which is still the most common data type used in biological, industrial and financial applications. In particular, it is challenging to transfer large-scale pre-trained models to downstream tasks defined on small tabular datasets. To address this, we propose VisTabNet -- a cross-modal transfer learning method, which allows for adapting Vision Transformer (ViT) with pre-trained weights to process tabular data. By projecting tabular inputs to patch embeddings acceptable by ViT, we can directly apply a pre-trained Transformer Encoder to tabular inputs. This approach eliminates the conceptual cost of designing a suitable architecture for processing tabular data, while reducing the computational cost of training the model from scratch. Experimental results on multiple small tabular datasets (less than 1k samples) demonstrate VisTabNet's superiority, outperforming both traditional ensemble methods and recent deep learning models. The proposed method goes beyond conventional transfer learning practice and shows that pre-trained image models can be transferred to solve tabular problems, extending the boundaries of transfer learning.

Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers (VTTs), a novel multimodal representation learning approach suited for model-based reinforcement learning and planning. Our approach extends the Visual Transformer dosovitskiy2021image to handle visuo-tactile feedback. Specifically, VTT uses tactile feedback together with self and cross-modal attention to build latent heatmap representations that focus attention on important task features in the visual domain. We demonstrate the efficacy of VTT for representation learning with a comparative evaluation against baselines on four simulated robot tasks and one real world block pushing task. We conduct an ablation study over the components of VTT to highlight the importance of cross-modality in representation learning.

We propose to improve transformers of a specific modality with irrelevant data from other modalities, e.g., improve an ImageNet model with audio or point cloud datasets. We would like to highlight that the data samples of the target modality are irrelevant to the other modalities, which distinguishes our method from other works utilizing paired (e.g., CLIP) or interleaved data of different modalities. We propose a methodology named Multimodal Pathway - given a target modality and a transformer designed for it, we use an auxiliary transformer trained with data of another modality and construct pathways to connect components of the two models so that data of the target modality can be processed by both models. In this way, we utilize the universal sequence-to-sequence modeling abilities of transformers obtained from two modalities. As a concrete implementation, we use a modality-specific tokenizer and task-specific head as usual but utilize the transformer blocks of the auxiliary model via a proposed method named Cross-Modal Re-parameterization, which exploits the auxiliary weights without any inference costs. On the image, point cloud, video, and audio recognition tasks, we observe significant and consistent performance improvements with irrelevant data from other modalities. The code and models are available at https://github.com/AILab-CVC/M2PT.

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e.g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e.g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

We present Magic Mirror, a framework for generating identity-preserved videos with cinematic-level quality and dynamic motion. While recent advances in video diffusion models have shown impressive capabilities in text-to-video generation, maintaining consistent identity while producing natural motion remains challenging. Previous methods either require person-specific fine-tuning or struggle to balance identity preservation with motion diversity. Built upon Video Diffusion Transformers, our method introduces three key components: (1) a dual-branch facial feature extractor that captures both identity and structural features, (2) a lightweight cross-modal adapter with Conditioned Adaptive Normalization for efficient identity integration, and (3) a two-stage training strategy combining synthetic identity pairs with video data. Extensive experiments demonstrate that Magic Mirror effectively balances identity consistency with natural motion, outperforming existing methods across multiple metrics while requiring minimal parameters added. The code and model will be made publicly available at: https://github.com/dvlab-research/MagicMirror/

The development of the transformer-based text-to-image models are impeded by its slow generation and complexity for high-resolution images. In this work, we put forward a solution based on hierarchical transformers and local parallel auto-regressive generation. We pretrain a 6B-parameter transformer with a simple and flexible self-supervised task, Cross-modal general language model (CogLM), and finetune it for fast super-resolution. The new text-to-image system, CogView2, shows very competitive generation compared to concurrent state-of-the-art DALL-E-2, and naturally supports interactive text-guided editing on images.

Speech-driven 3D facial animation is challenging due to the complex geometry of human faces and the limited availability of 3D audio-visual data. Prior works typically focus on learning phoneme-level features of short audio windows with limited context, occasionally resulting in inaccurate lip movements. To tackle this limitation, we propose a Transformer-based autoregressive model, FaceFormer, which encodes the long-term audio context and autoregressively predicts a sequence of animated 3D face meshes. To cope with the data scarcity issue, we integrate the self-supervised pre-trained speech representations. Also, we devise two biased attention mechanisms well suited to this specific task, including the biased cross-modal multi-head (MH) attention and the biased causal MH self-attention with a periodic positional encoding strategy. The former effectively aligns the audio-motion modalities, whereas the latter offers abilities to generalize to longer audio sequences. Extensive experiments and a perceptual user study show that our approach outperforms the existing state-of-the-arts. The code will be made available.

With the continuous improvements of deepfake methods, forgery messages have transitioned from single-modality to multi-modal fusion, posing new challenges for existing forgery detection algorithms. In this paper, we propose AVT2-DWF, the Audio-Visual dual Transformers grounded in Dynamic Weight Fusion, which aims to amplify both intra- and cross-modal forgery cues, thereby enhancing detection capabilities. AVT2-DWF adopts a dual-stage approach to capture both spatial characteristics and temporal dynamics of facial expressions. This is achieved through a face transformer with an n-frame-wise tokenization strategy encoder and an audio transformer encoder. Subsequently, it uses multi-modal conversion with dynamic weight fusion to address the challenge of heterogeneous information fusion between audio and visual modalities. Experiments on DeepfakeTIMIT, FakeAVCeleb, and DFDC datasets indicate that AVT2-DWF achieves state-of-the-art performance intra- and cross-dataset Deepfake detection. Code is available at https://github.com/raining-dev/AVT2-DWF.

Accurate medical classification requires a large number of multi-modal data, and in many cases, different feature types. Previous studies have shown promising results when using multi-modal data, outperforming single-modality models when classifying diseases such as Alzheimer's Disease (AD). However, those models are usually not flexible enough to handle missing modalities. Currently, the most common workaround is discarding samples with missing modalities which leads to considerable data under-utilization. Adding to the fact that labeled medical images are already scarce, the performance of data-driven methods like deep learning can be severely hampered. Therefore, a multi-modal method that can handle missing data in various clinical settings is highly desirable. In this paper, we present Multi-Modal Mixing Transformer (3MAT), a disease classification transformer that not only leverages multi-modal data but also handles missing data scenarios. In this work, we test 3MT for AD and Cognitively normal (CN) classification and mild cognitive impairment (MCI) conversion prediction to progressive MCI (pMCI) or stable MCI (sMCI) using clinical and neuroimaging data. The model uses a novel Cascaded Modality Transformer architecture with cross-attention to incorporate multi-modal information for more informed predictions. We propose a novel modality dropout mechanism to ensure an unprecedented level of modality independence and robustness to handle missing data scenarios. The result is a versatile network that enables the mixing of arbitrary numbers of modalities with different feature types and also ensures full data utilization missing data scenarios. The model is trained and evaluated on the ADNI dataset with the SOTRA performance and further evaluated with the AIBL dataset with missing data.

The widespread dissemination of Deepfakes demands effective approaches that can detect perceptually convincing forged images. In this paper, we aim to capture the subtle manipulation artifacts at different scales using transformer models. In particular, we introduce a Multi-modal Multi-scale TRansformer (M2TR), which operates on patches of different sizes to detect local inconsistencies in images at different spatial levels. M2TR further learns to detect forgery artifacts in the frequency domain to complement RGB information through a carefully designed cross modality fusion block. In addition, to stimulate Deepfake detection research, we introduce a high-quality Deepfake dataset, SR-DF, which consists of 4,000 DeepFake videos generated by state-of-the-art face swapping and facial reenactment methods. We conduct extensive experiments to verify the effectiveness of the proposed method, which outperforms state-of-the-art Deepfake detection methods by clear margins.

In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the image and point clouds tokens as inputs and directly outputs accurate 3D bounding boxes. The spatial alignment of multi-modal tokens is performed by encoding the 3D points into multi-modal features. The core design of CMT is quite simple while its performance is impressive. It achieves 74.1\% NDS (state-of-the-art with single model) on nuScenes test set while maintaining faster inference speed. Moreover, CMT has a strong robustness even if the LiDAR is missing. Code is released at https://github.com/junjie18/CMT.

Jointly processing information from multiple sensors is crucial to achieving accurate and robust perception for reliable autonomous driving systems. However, current 3D perception research follows a modality-specific paradigm, leading to additional computation overheads and inefficient collaboration between different sensor data. In this paper, we present an efficient multi-modal backbone for outdoor 3D perception named UniTR, which processes a variety of modalities with unified modeling and shared parameters. Unlike previous works, UniTR introduces a modality-agnostic transformer encoder to handle these view-discrepant sensor data for parallel modal-wise representation learning and automatic cross-modal interaction without additional fusion steps. More importantly, to make full use of these complementary sensor types, we present a novel multi-modal integration strategy by both considering semantic-abundant 2D perspective and geometry-aware 3D sparse neighborhood relations. UniTR is also a fundamentally task-agnostic backbone that naturally supports different 3D perception tasks. It sets a new state-of-the-art performance on the nuScenes benchmark, achieving +1.1 NDS higher for 3D object detection and +12.0 higher mIoU for BEV map segmentation with lower inference latency. Code will be available at https://github.com/Haiyang-W/UniTR .

Data-driven and controllable human motion synthesis and prediction are active research areas with various applications in interactive media and social robotics. Challenges remain in these fields for generating diverse motions given past observations and dealing with imperfect poses. This paper introduces MoDiff, an autoregressive probabilistic diffusion model over motion sequences conditioned on control contexts of other modalities. Our model integrates a cross-modal Transformer encoder and a Transformer-based decoder, which are found effective in capturing temporal correlations in motion and control modalities. We also introduce a new data dropout method based on the diffusion forward process to provide richer data representations and robust generation. We demonstrate the superior performance of MoDiff in controllable motion synthesis for locomotion with respect to two baselines and show the benefits of diffusion data dropout for robust synthesis and reconstruction of high-fidelity motion close to recorded data.

We propose a novel task for generating 3D dance movements that simultaneously incorporate both text and music modalities. Unlike existing works that generate dance movements using a single modality such as music, our goal is to produce richer dance movements guided by the instructive information provided by the text. However, the lack of paired motion data with both music and text modalities limits the ability to generate dance movements that integrate both. To alleviate this challenge, we propose to utilize a 3D human motion VQ-VAE to project the motions of the two datasets into a latent space consisting of quantized vectors, which effectively mix the motion tokens from the two datasets with different distributions for training. Additionally, we propose a cross-modal transformer to integrate text instructions into motion generation architecture for generating 3D dance movements without degrading the performance of music-conditioned dance generation. To better evaluate the quality of the generated motion, we introduce two novel metrics, namely Motion Prediction Distance (MPD) and Freezing Score, to measure the coherence and freezing percentage of the generated motion. Extensive experiments show that our approach can generate realistic and coherent dance movements conditioned on both text and music while maintaining comparable performance with the two single modalities. Code will be available at: https://garfield-kh.github.io/TM2D/.

We introduce Sketch-based Video Object Localization (SVOL), a new task aimed at localizing spatio-temporal object boxes in video queried by the input sketch. We first outline the challenges in the SVOL task and build the Sketch-Video Attention Network (SVANet) with the following design principles: (i) to consider temporal information of video and bridge the domain gap between sketch and video; (ii) to accurately identify and localize multiple objects simultaneously; (iii) to handle various styles of sketches; (iv) to be classification-free. In particular, SVANet is equipped with a Cross-modal Transformer that models the interaction between learnable object tokens, query sketch, and video through attention operations, and learns upon a per-frame set matching strategy that enables frame-wise prediction while utilizing global video context. We evaluate SVANet on a newly curated SVOL dataset. By design, SVANet successfully learns the mapping between the query sketches and video objects, achieving state-of-the-art results on the SVOL benchmark. We further confirm the effectiveness of SVANet via extensive ablation studies and visualizations. Lastly, we demonstrate its transfer capability on unseen datasets and novel categories, suggesting its high scalability in real-world applications.

We present AIST++, a new multi-modal dataset of 3D dance motion and music, along with FACT, a Full-Attention Cross-modal Transformer network for generating 3D dance motion conditioned on music. The proposed AIST++ dataset contains 5.2 hours of 3D dance motion in 1408 sequences, covering 10 dance genres with multi-view videos with known camera poses -- the largest dataset of this kind to our knowledge. We show that naively applying sequence models such as transformers to this dataset for the task of music conditioned 3D motion generation does not produce satisfactory 3D motion that is well correlated with the input music. We overcome these shortcomings by introducing key changes in its architecture design and supervision: FACT model involves a deep cross-modal transformer block with full-attention that is trained to predict N future motions. We empirically show that these changes are key factors in generating long sequences of realistic dance motion that are well-attuned to the input music. We conduct extensive experiments on AIST++ with user studies, where our method outperforms recent state-of-the-art methods both qualitatively and quantitatively.

We present AdVerb, a novel audio-visual dereverberation framework that uses visual cues in addition to the reverberant sound to estimate clean audio. Although audio-only dereverberation is a well-studied problem, our approach incorporates the complementary visual modality to perform audio dereverberation. Given an image of the environment where the reverberated sound signal has been recorded, AdVerb employs a novel geometry-aware cross-modal transformer architecture that captures scene geometry and audio-visual cross-modal relationship to generate a complex ideal ratio mask, which, when applied to the reverberant audio predicts the clean sound. The effectiveness of our method is demonstrated through extensive quantitative and qualitative evaluations. Our approach significantly outperforms traditional audio-only and audio-visual baselines on three downstream tasks: speech enhancement, speech recognition, and speaker verification, with relative improvements in the range of 18% - 82% on the LibriSpeech test-clean set. We also achieve highly satisfactory RT60 error scores on the AVSpeech dataset.

We present HERO, a novel framework for large-scale video+language omni-representation learning. HERO encodes multimodal inputs in a hierarchical structure, where local context of a video frame is captured by a Cross-modal Transformer via multimodal fusion, and global video context is captured by a Temporal Transformer. In addition to standard Masked Language Modeling (MLM) and Masked Frame Modeling (MFM) objectives, we design two new pre-training tasks: (i) Video-Subtitle Matching (VSM), where the model predicts both global and local temporal alignment; and (ii) Frame Order Modeling (FOM), where the model predicts the right order of shuffled video frames. HERO is jointly trained on HowTo100M and large-scale TV datasets to gain deep understanding of complex social dynamics with multi-character interactions. Comprehensive experiments demonstrate that HERO achieves new state of the art on multiple benchmarks over Text-based Video/Video-moment Retrieval, Video Question Answering (QA), Video-and-language Inference and Video Captioning tasks across different domains. We also introduce two new challenging benchmarks How2QA and How2R for Video QA and Retrieval, collected from diverse video content over multimodalities.

This paper addresses the problem of cross-modal object tracking from RGB videos and event data. Rather than constructing a complex cross-modal fusion network, we explore the great potential of a pre-trained vision Transformer (ViT). Particularly, we delicately investigate plug-and-play training augmentations that encourage the ViT to bridge the vast distribution gap between the two modalities, enabling comprehensive cross-modal information interaction and thus enhancing its ability. Specifically, we propose a mask modeling strategy that randomly masks a specific modality of some tokens to enforce the interaction between tokens from different modalities interacting proactively. To mitigate network oscillations resulting from the masking strategy and further amplify its positive effect, we then theoretically propose an orthogonal high-rank loss to regularize the attention matrix. Extensive experiments demonstrate that our plug-and-play training augmentation techniques can significantly boost state-of-the-art one-stream and twostream trackers to a large extent in terms of both tracking precision and success rate. Our new perspective and findings will potentially bring insights to the field of leveraging powerful pre-trained ViTs to model cross-modal data. The code will be publicly available.

An important challenge in vision-based action recognition is the embedding of spatiotemporal features with two or more heterogeneous modalities into a single feature. In this study, we propose a new 3D deformable transformer for action recognition with adaptive spatiotemporal receptive fields and a cross-modal learning scheme. The 3D deformable transformer consists of three attention modules: 3D deformability, local joint stride, and temporal stride attention. The two cross-modal tokens are input into the 3D deformable attention module to create a cross-attention token with a reflected spatiotemporal correlation. Local joint stride attention is applied to spatially combine attention and pose tokens. Temporal stride attention temporally reduces the number of input tokens in the attention module and supports temporal expression learning without the simultaneous use of all tokens. The deformable transformer iterates L-times and combines the last cross-modal token for classification. The proposed 3D deformable transformer was tested on the NTU60, NTU120, FineGYM, and PennAction datasets, and showed results better than or similar to pre-trained state-of-the-art methods even without a pre-training process. In addition, by visualizing important joints and correlations during action recognition through spatial joint and temporal stride attention, the possibility of achieving an explainable potential for action recognition is presented.

Zero-shot learning (ZSL) aims to predict unseen classes whose samples have never appeared during training. One of the most effective and widely used semantic information for zero-shot image classification are attributes which are annotations for class-level visual characteristics. However, the current methods often fail to discriminate those subtle visual distinctions between images due to not only the shortage of fine-grained annotations, but also the attribute imbalance and co-occurrence. In this paper, we present a transformer-based end-to-end ZSL method named DUET, which integrates latent semantic knowledge from the pre-trained language models (PLMs) via a self-supervised multi-modal learning paradigm. Specifically, we (1) developed a cross-modal semantic grounding network to investigate the model's capability of disentangling semantic attributes from the images; (2) applied an attribute-level contrastive learning strategy to further enhance the model's discrimination on fine-grained visual characteristics against the attribute co-occurrence and imbalance; (3) proposed a multi-task learning policy for considering multi-model objectives. We find that our DUET can achieve state-of-the-art performance on three standard ZSL benchmarks and a knowledge graph equipped ZSL benchmark. Its components are effective and its predictions are interpretable.

Application developers advertise their Apps by creating product pages with App images, and bidding on search terms. It is then crucial for App images to be highly relevant with the search terms. Solutions to this problem require an image-text matching model to predict the quality of the match between the chosen image and the search terms. In this work, we present a novel approach to matching an App image to search terms based on fine-tuning a pre-trained LXMERT model. We show that compared to the CLIP model and a baseline using a Transformer model for search terms, and a ResNet model for images, we significantly improve the matching accuracy. We evaluate our approach using two sets of labels: advertiser associated (image, search term) pairs for a given application, and human ratings for the relevance between (image, search term) pairs. Our approach achieves 0.96 AUC score for advertiser associated ground truth, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 8% and 14%. For human labeled ground truth, our approach achieves 0.95 AUC score, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 16% and 17%.

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant challenges to existing RVOS methods. With this in mind, we propose a simple yet effective model with a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. The CMA module builds multimodal affinity with a few samples, thus quickly learning new semantic information, and enabling the model to adapt to different scenarios. Since the proposed method targets limited samples for new scenes, we generalize the problem as - few-shot referring video object segmentation (FS-RVOS). To foster research in this direction, we build up a new FS-RVOS benchmark based on currently available datasets. The benchmark covers a wide range and includes multiple situations, which can maximally simulate real-world scenarios. Extensive experiments show that our model adapts well to different scenarios with only a few samples, reaching state-of-the-art performance on the benchmark. On Mini-Ref-YouTube-VOS, our model achieves an average performance of 53.1 J and 54.8 F, which are 10% better than the baselines. Furthermore, we show impressive results of 77.7 J and 74.8 F on Mini-Ref-SAIL-VOS, which are significantly better than the baselines. Code is publicly available at https://github.com/hengliusky/Few_shot_RVOS.

We present AstroCLIP, a strategy to facilitate the construction of astronomical foundation models that bridge the gap between diverse observational modalities. We demonstrate that a cross-modal contrastive learning approach between images and optical spectra of galaxies yields highly informative embeddings of both modalities. In particular, we apply our method on multi-band images and optical spectra from the Dark Energy Spectroscopic Instrument (DESI), and show that: (1) these embeddings are well-aligned between modalities and can be used for accurate cross-modal searches, and (2) these embeddings encode valuable physical information about the galaxies -- in particular redshift and stellar mass -- that can be used to achieve competitive zero- and few- shot predictions without further finetuning. Additionally, in the process of developing our approach, we also construct a novel, transformer-based model and pretraining approach for processing galaxy spectra.

Large Language Models (LLMs) demonstrate remarkable generalizability across diverse tasks, yet genomic foundation models (GFMs) still require separate finetuning for each downstream application, creating significant overhead as model sizes grow. Moreover, existing GFMs are constrained by rigid output formats, limiting their applicability to various genomic tasks. In this work, we revisit the transformer-based auto-regressive models and introduce Omni-DNA, a family of cross-modal multi-task models ranging from 20 million to 1 billion parameters. Our approach consists of two stages: (i) pretraining on DNA sequences with next token prediction objective, and (ii) expanding the multi-modal task-specific tokens and finetuning for multiple downstream tasks simultaneously. When evaluated on the Nucleotide Transformer and GB benchmarks, Omni-DNA achieves state-of-the-art performance on 18 out of 26 tasks. Through multi-task finetuning, Omni-DNA addresses 10 acetylation and methylation tasks at once, surpassing models trained on each task individually. Finally, we design two complex genomic tasks, DNA2Function and Needle-in-DNA, which map DNA sequences to textual functional descriptions and images, respectively, indicating Omni-DNA's cross-modal capabilities to broaden the scope of genomic applications. All the models are available through https://huggingface.co/collections/zehui127

We learn a visual representation that captures information about the camera that recorded a given photo. To do this, we train a multimodal embedding between image patches and the EXIF metadata that cameras automatically insert into image files. Our model represents this metadata by simply converting it to text and then processing it with a transformer. The features that we learn significantly outperform other self-supervised and supervised features on downstream image forensics and calibration tasks. In particular, we successfully localize spliced image regions "zero shot" by clustering the visual embeddings for all of the patches within an image.

Video Highlight Detection and Moment Retrieval (HD/MR) are essential in video analysis. Recent joint prediction transformer models often overlook their cross-task dynamics and video-text alignment and refinement. Moreover, most models typically use limited, uni-directional attention mechanisms, resulting in weakly integrated representations and suboptimal performance in capturing the interdependence between video and text modalities. Although large-language and vision-language models (LLM/LVLMs) have gained prominence across various domains, their application in this field remains relatively underexplored. Here we propose VideoLights, a novel HD/MR framework addressing these limitations through (i) Convolutional Projection and Feature Refinement modules with an alignment loss for better video-text feature alignment, (ii) Bi-Directional Cross-Modal Fusion network for strongly coupled query-aware clip representations, and (iii) Uni-directional joint-task feedback mechanism enhancing both tasks through correlation. In addition, (iv) we introduce hard positive/negative losses for adaptive error penalization and improved learning, and (v) leverage LVLMs like BLIP-2 for enhanced multimodal feature integration and intelligent pretraining using synthetic data generated from LVLMs. Comprehensive experiments on QVHighlights, TVSum, and Charades-STA benchmarks demonstrate state-of-the-art performance. Codes and models are available at https://github.com/dpaul06/VideoLights .

Recently, text-to-image generation models have achieved remarkable advancements, particularly with diffusion models facilitating high-quality image synthesis from textual descriptions. However, these models often struggle with achieving precise control over pixel-level layouts, object appearances, and global styles when using text prompts alone. To mitigate this issue, previous works introduce conditional images as auxiliary inputs for image generation, enhancing control but typically necessitating specialized models tailored to different types of reference inputs. In this paper, we explore a new approach to unify controllable generation within a single framework. Specifically, we propose the unified image-instruction adapter (UNIC-Adapter) built on the Multi-Modal-Diffusion Transformer architecture, to enable flexible and controllable generation across diverse conditions without the need for multiple specialized models. Our UNIC-Adapter effectively extracts multi-modal instruction information by incorporating both conditional images and task instructions, injecting this information into the image generation process through a cross-attention mechanism enhanced by Rotary Position Embedding. Experimental results across a variety of tasks, including pixel-level spatial control, subject-driven image generation, and style-image-based image synthesis, demonstrate the effectiveness of our UNIC-Adapter in unified controllable image generation.

ORCA (Shen et al., 2023) is a recent technique for cross-modal fine-tuning, i.e., applying pre-trained transformer models to modalities beyond their training data. The technique consists primarily of training an embedder and fine-tuning the embedder and model. Despite its high performance on a variety of downstream tasks, we do not understand precisely how each of these components contribute to ORCA's success. Therefore, we run a series of ablations and find that embedder training does not help 2D tasks at all, contrary to what the original paper posits. In 1D tasks, some amount of embedder training is necessary but more is not better. In 4 out of 6 datasets we experiment with, it is model fine-tuning that makes the biggest difference. Through our ablations and baselines, we contribute a better understanding of the individual components of ORCA.

We propose Unicoder-VL, a universal encoder that aims to learn joint representations of vision and language in a pre-training manner. Borrow ideas from cross-lingual pre-trained models, such as XLM and Unicoder, both visual and linguistic contents are fed into a multi-layer Transformer for the cross-modal pre-training, where three pre-trained tasks are employed, including Masked Language Modeling (MLM), Masked Object Classification (MOC) and Visual-linguistic Matching (VLM). The first two tasks learn context-aware representations for input tokens based on linguistic and visual contents jointly. The last task tries to predict whether an image and a text describe each other. After pretraining on large-scale image-caption pairs, we transfer Unicoder-VL to caption-based image-text retrieval and visual commonsense reasoning, with just one additional output layer. We achieve state-of-the-art or comparable results on both two tasks and show the powerful ability of the cross-modal pre-training.

In this paper, we present the Logically submissions to De-Factify 2 challenge (DE-FACTIFY 2023) on the task 1 of Multi-Modal Fact Checking. We describes our submissions to this challenge including explored evidence retrieval and selection techniques, pre-trained cross-modal and unimodal models, and a cross-modal veracity model based on the well established Transformer Encoder (TE) architecture which is heavily relies on the concept of self-attention. Exploratory analysis is also conducted on this Factify 2 data set that uncovers the salient multi-modal patterns and hypothesis motivating the architecture proposed in this work. A series of preliminary experiments were done to investigate and benchmarking different pre-trained embedding models, evidence retrieval settings and thresholds. The final system, a standard two-stage evidence based veracity detection system, yields weighted avg. 0.79 on both val set and final blind test set on the task 1, which achieves 3rd place with a small margin to the top performing system on the leaderboard among 9 participants.

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city. Our contributions are threefold. First, we propose a novel method for cross-modal unsupervised learning of semantic image segmentation by leveraging synchronized LiDAR and image data. The key ingredient of our method is the use of an object proposal module that analyzes the LiDAR point cloud to obtain proposals for spatially consistent objects. Second, we show that these 3D object proposals can be aligned with the input images and reliably clustered into semantically meaningful pseudo-classes. Finally, we develop a cross-modal distillation approach that leverages image data partially annotated with the resulting pseudo-classes to train a transformer-based model for image semantic segmentation. We show the generalization capabilities of our method by testing on four different testing datasets (Cityscapes, Dark Zurich, Nighttime Driving and ACDC) without any finetuning, and demonstrate significant improvements compared to the current state of the art on this problem. See project webpage https://vobecant.github.io/DriveAndSegment/ for the code and more.

Natural language (NL) based vehicle retrieval is a task aiming to retrieve a vehicle that is most consistent with a given NL query from among all candidate vehicles. Because NL query can be easily obtained, such a task has a promising prospect in building an interactive intelligent traffic system (ITS). Current solutions mainly focus on extracting both text and image features and mapping them to the same latent space to compare the similarity. However, existing methods usually use dependency analysis or semantic role-labelling techniques to find keywords related to vehicle attributes. These techniques may require a lot of pre-processing and post-processing work, and also suffer from extracting the wrong keyword when the NL query is complex. To tackle these problems and simplify, we borrow the idea from named entity recognition (NER) and construct FindVehicle, a NER dataset in the traffic domain. It has 42.3k labelled NL descriptions of vehicle tracks, containing information such as the location, orientation, type and colour of the vehicle. FindVehicle also adopts both overlapping entities and fine-grained entities to meet further requirements. To verify its effectiveness, we propose a baseline NL-based vehicle retrieval model called VehicleFinder. Our experiment shows that by using text encoders pre-trained by FindVehicle, VehicleFinder achieves 87.7\% precision and 89.4\% recall when retrieving a target vehicle by text command on our homemade dataset based on UA-DETRAC. The time cost of VehicleFinder is 279.35 ms on one ARM v8.2 CPU and 93.72 ms on one RTX A4000 GPU, which is much faster than the Transformer-based system. The dataset is open-source via the link https://github.com/GuanRunwei/FindVehicle, and the implementation can be found via the link https://github.com/GuanRunwei/VehicleFinder-CTIM.

Training diffusion models for audiovisual sequences allows for a range of generation tasks by learning conditional distributions of various input-output combinations of the two modalities. Nevertheless, this strategy often requires training a separate model for each task which is expensive. Here, we propose a novel training approach to effectively learn arbitrary conditional distributions in the audiovisual space.Our key contribution lies in how we parameterize the diffusion timestep in the forward diffusion process. Instead of the standard fixed diffusion timestep, we propose applying variable diffusion timesteps across the temporal dimension and across modalities of the inputs. This formulation offers flexibility to introduce variable noise levels for various portions of the input, hence the term mixture of noise levels. We propose a transformer-based audiovisual latent diffusion model and show that it can be trained in a task-agnostic fashion using our approach to enable a variety of audiovisual generation tasks at inference time. Experiments demonstrate the versatility of our method in tackling cross-modal and multimodal interpolation tasks in the audiovisual space. Notably, our proposed approach surpasses baselines in generating temporally and perceptually consistent samples conditioned on the input. Project page: avdit2024.github.io

Pre-training of text and layout has proved effective in a variety of visually-rich document understanding tasks due to its effective model architecture and the advantage of large-scale unlabeled scanned/digital-born documents. We propose LayoutLMv2 architecture with new pre-training tasks to model the interaction among text, layout, and image in a single multi-modal framework. Specifically, with a two-stream multi-modal Transformer encoder, LayoutLMv2 uses not only the existing masked visual-language modeling task but also the new text-image alignment and text-image matching tasks, which make it better capture the cross-modality interaction in the pre-training stage. Meanwhile, it also integrates a spatial-aware self-attention mechanism into the Transformer architecture so that the model can fully understand the relative positional relationship among different text blocks. Experiment results show that LayoutLMv2 outperforms LayoutLM by a large margin and achieves new state-of-the-art results on a wide variety of downstream visually-rich document understanding tasks, including FUNSD (0.7895 to 0.8420), CORD (0.9493 to 0.9601), SROIE (0.9524 to 0.9781), Kleister-NDA (0.8340 to 0.8520), RVL-CDIP (0.9443 to 0.9564), and DocVQA (0.7295 to 0.8672). We made our model and code publicly available at https://aka.ms/layoutlmv2.

Large Language Models (LLMs) have made significant strides in text generation and comprehension, with recent advancements extending into multimodal LLMs that integrate visual and audio inputs. However, these models continue to struggle with fine-grained, cross-modal temporal understanding, particularly when correlating events across audio and video streams. We address these challenges with two key contributions: a new dataset and model, called OCTAV and OMCAT respectively. OCTAV (Omni Context and Temporal Audio Video) is a novel dataset designed to capture event transitions across audio and video. Second, OMCAT (Omni Context Aware Transformer) is a powerful model that leverages RoTE (Rotary Time Embeddings), an innovative extension of RoPE, to enhance temporal grounding and computational efficiency in time-anchored tasks. Through a robust three-stage training pipeline-feature alignment, instruction tuning, and OCTAV-specific training-OMCAT excels in cross-modal temporal understanding. Our model demonstrates state-of-the-art performance on Audio-Visual Question Answering (AVQA) tasks and the OCTAV benchmark, showcasing significant gains in temporal reasoning and cross-modal alignment, as validated through comprehensive experiments and ablation studies. Our dataset and code will be made publicly available. The link to our demo page is https://om-cat.github.io.

Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works usually adopt dynamic graph networks to indirectly model the intra/inter-modal interactions, making the model difficult to distinguish the referred object from distractors due to the monolithic representations of visual and linguistic contents. In this work, we exploit Transformer for its natural suitability on permutation-invariant 3D point clouds data and propose a TransRefer3D network to extract entity-and-relation aware multimodal context among objects for more discriminative feature learning. Concretely, we devise an Entity-aware Attention (EA) module and a Relation-aware Attention (RA) module to conduct fine-grained cross-modal feature matching. Facilitated by co-attention operation, our EA module matches visual entity features with linguistic entity features while RA module matches pair-wise visual relation features with linguistic relation features, respectively. We further integrate EA and RA modules into an Entity-and-Relation aware Contextual Block (ERCB) and stack several ERCBs to form our TransRefer3D for hierarchical multimodal context modeling. Extensive experiments on both Nr3D and Sr3D datasets demonstrate that our proposed model significantly outperforms existing approaches by up to 10.6% and claims the new state-of-the-art. To the best of our knowledge, this is the first work investigating Transformer architecture for fine-grained 3D visual grounding task.

Video-and-language pre-training has shown promising improvements on various downstream tasks. Most previous methods capture cross-modal interactions with a transformer-based multimodal encoder, not fully addressing the misalignment between unimodal video and text features. Besides, learning fine-grained visual-language alignment usually requires off-the-shelf object detectors to provide object information, which is bottlenecked by the detector's limited vocabulary and expensive computation cost. We propose Align and Prompt: an efficient and effective video-and-language pre-training framework with better cross-modal alignment. First, we introduce a video-text contrastive (VTC) loss to align unimodal video-text features at the instance level, which eases the modeling of cross-modal interactions. Then, we propose a new visually-grounded pre-training task, prompting entity modeling (PEM), which aims to learn fine-grained region-entity alignment. To achieve this, we first introduce an entity prompter module, which is trained with VTC to produce the similarity between a video crop and text prompts instantiated with entity names. The PEM task then asks the model to predict the entity pseudo-labels (i.e~normalized similarity scores) for randomly-selected video crops. The resulting pre-trained model achieves state-of-the-art performance on both text-video retrieval and videoQA, outperforming prior work by a substantial margin. Our code and pre-trained models are available at https://github.com/salesforce/ALPRO.

Humans use different modalities, such as speech, text, images, videos, etc., to communicate their intent and goals with teammates. For robots to become better assistants, we aim to endow them with the ability to follow instructions and understand tasks specified by their human partners. Most robotic policy learning methods have focused on one single modality of task specification while ignoring the rich cross-modal information. We present MUTEX, a unified approach to policy learning from multimodal task specifications. It trains a transformer-based architecture to facilitate cross-modal reasoning, combining masked modeling and cross-modal matching objectives in a two-stage training procedure. After training, MUTEX can follow a task specification in any of the six learned modalities (video demonstrations, goal images, text goal descriptions, text instructions, speech goal descriptions, and speech instructions) or a combination of them. We systematically evaluate the benefits of MUTEX in a newly designed dataset with 100 tasks in simulation and 50 tasks in the real world, annotated with multiple instances of task specifications in different modalities, and observe improved performance over methods trained specifically for any single modality. More information at https://ut-austin-rpl.github.io/MUTEX/

In this work, we construct the largest dataset for multimodal pretraining in Chinese, which consists of over 1.9TB images and 292GB texts that cover a wide range of domains. We propose a cross-modal pretraining method called M6, referring to Multi-Modality to Multi-Modality Multitask Mega-transformer, for unified pretraining on the data of single modality and multiple modalities. We scale the model size up to 10 billion and 100 billion parameters, and build the largest pretrained model in Chinese. We apply the model to a series of downstream applications, and demonstrate its outstanding performance in comparison with strong baselines. Furthermore, we specifically design a downstream task of text-guided image generation, and show that the finetuned M6 can create high-quality images with high resolution and abundant details.

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end diffusion model for multi-modal understanding and generation that significantly improves on existing diffusion-based multimodal models, and is the first of its kind to support the full suite of vision-language modeling capabilities. Inspired by the multimodal diffusion transformer (MM-DiT) and recent advances in discrete diffusion language modeling, we leverage a cross-modal maximum likelihood estimation framework that simultaneously trains the conditional likelihoods of both images and text jointly under a single loss function, which is back-propagated through both branches of the diffusion transformer. The resulting model is highly flexible and capable of a wide range of tasks including image generation, captioning, and visual question answering. Our model attained competitive performance compared to recent unified image understanding and generation models, demonstrating the potential of multimodal diffusion modeling as a promising alternative to autoregressive next-token prediction models.

The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rendering end-to-end training increasingly prohibitive. In this paper, we propose NEVLP, a noise-robust framework for efficient vision-language pre-training that requires less pre-training data. Specifically, we bridge the modality gap between a frozen image encoder and a large language model with a transformer and introduce two innovative learning strategies: noise-adaptive learning and concept-enhanced learning to mitigate the impact of noise. In noise-adaptive learning, we estimate the noise probability of each image-text pair based on the transformer's memorization effect and employ noise-adaptive regularization on image-text contrastive learning to condition cross-modal alignment. In concept-enhanced learning, we enrich incomplete text by incorporating visual concepts (objects in the image) to provide prior information about existing objects for image-text matching and image-grounded text generation, thereby mitigating text incompletion. Our framework effectively utilizes noisy web data and achieves state-of-the-art performance with less pre-training data across a wide range of vision-language tasks, including image-text retrieval, image captioning, and visual question answering.

Vision-and-language reasoning requires an understanding of visual concepts, language semantics, and, most importantly, the alignment and relationships between these two modalities. We thus propose the LXMERT (Learning Cross-Modality Encoder Representations from Transformers) framework to learn these vision-and-language connections. In LXMERT, we build a large-scale Transformer model that consists of three encoders: an object relationship encoder, a language encoder, and a cross-modality encoder. Next, to endow our model with the capability of connecting vision and language semantics, we pre-train the model with large amounts of image-and-sentence pairs, via five diverse representative pre-training tasks: masked language modeling, masked object prediction (feature regression and label classification), cross-modality matching, and image question answering. These tasks help in learning both intra-modality and cross-modality relationships. After fine-tuning from our pre-trained parameters, our model achieves the state-of-the-art results on two visual question answering datasets (i.e., VQA and GQA). We also show the generalizability of our pre-trained cross-modality model by adapting it to a challenging visual-reasoning task, NLVR2, and improve the previous best result by 22% absolute (54% to 76%). Lastly, we demonstrate detailed ablation studies to prove that both our novel model components and pre-training strategies significantly contribute to our strong results; and also present several attention visualizations for the different encoders. Code and pre-trained models publicly available at: https://github.com/airsplay/lxmert

Sora-like video generation models have achieved remarkable progress with a Multi-Modal Diffusion Transformer MM-DiT architecture. However, the current video generation models predominantly focus on single-prompt, struggling to generate coherent scenes with multiple sequential prompts that better reflect real-world dynamic scenarios. While some pioneering works have explored multi-prompt video generation, they face significant challenges including strict training data requirements, weak prompt following, and unnatural transitions. To address these problems, we propose DiTCtrl, a training-free multi-prompt video generation method under MM-DiT architectures for the first time. Our key idea is to take the multi-prompt video generation task as temporal video editing with smooth transitions. To achieve this goal, we first analyze MM-DiT's attention mechanism, finding that the 3D full attention behaves similarly to that of the cross/self-attention blocks in the UNet-like diffusion models, enabling mask-guided precise semantic control across different prompts with attention sharing for multi-prompt video generation. Based on our careful design, the video generated by DiTCtrl achieves smooth transitions and consistent object motion given multiple sequential prompts without additional training. Besides, we also present MPVBench, a new benchmark specially designed for multi-prompt video generation to evaluate the performance of multi-prompt generation. Extensive experiments demonstrate that our method achieves state-of-the-art performance without additional training.

While large-scale robotic systems typically rely on textual instructions for tasks, this work explores a different approach: can robots infer the task directly from observing humans? This shift necessitates the robot's ability to decode human intent and translate it into executable actions within its physical constraints and environment. We introduce Vid2Robot, a novel end-to-end video-based learning framework for robots. Given a video demonstration of a manipulation task and current visual observations, Vid2Robot directly produces robot actions. This is achieved through a unified representation model trained on a large dataset of human video and robot trajectory. The model leverages cross-attention mechanisms to fuse prompt video features to the robot's current state and generate appropriate actions that mimic the observed task. To further improve policy performance, we propose auxiliary contrastive losses that enhance the alignment between human and robot video representations. We evaluate Vid2Robot on real-world robots, demonstrating a 20% improvement in performance compared to other video-conditioned policies when using human demonstration videos. Additionally, our model exhibits emergent capabilities, such as successfully transferring observed motions from one object to another, and long-horizon composition, thus showcasing its potential for real-world applications. Project website: vid2robot.github.io

Many interpretable AI approaches have been proposed to provide plausible explanations for a model's decision-making. However, configuring an explainable model that effectively communicates among computational modules has received less attention. A recently proposed shared global workspace theory showed that networks of distributed modules can benefit from sharing information with a bottlenecked memory because the communication constraints encourage specialization, compositionality, and synchronization among the modules. Inspired by this, we propose Concept-Centric Transformers, a simple yet effective configuration of the shared global workspace for interpretability, consisting of: i) an object-centric-based memory module for extracting semantic concepts from input features, ii) a cross-attention mechanism between the learned concept and input embeddings, and iii) standard classification and explanation losses to allow human analysts to directly assess an explanation for the model's classification reasoning. We test our approach against other existing concept-based methods on classification tasks for various datasets, including CIFAR100, CUB-200-2011, and ImageNet, and we show that our model achieves better classification accuracy than all baselines across all problems but also generates more consistent concept-based explanations of classification output.

Recent work has demonstrated the effectiveness of cross-lingual language model pretraining for cross-lingual understanding. In this study, we present the results of two larger multilingual masked language models, with 3.5B and 10.7B parameters. Our two new models dubbed XLM-R XL and XLM-R XXL outperform XLM-R by 1.8% and 2.4% average accuracy on XNLI. Our model also outperforms the RoBERTa-Large model on several English tasks of the GLUE benchmark by 0.3% on average while handling 99 more languages. This suggests pretrained models with larger capacity may obtain both strong performance on high-resource languages while greatly improving low-resource languages. We make our code and models publicly available.

Transformers have revolutionized machine learning with their simple yet effective architecture. Pre-training Transformers on massive text datasets from the Internet has led to unmatched generalization for natural language understanding (NLU) tasks. However, such language models remain fragile when tasked with algorithmic forms of reasoning, where computations must be precise and robust. To address this limitation, we propose a novel approach that combines the Transformer's language understanding with the robustness of graph neural network (GNN)-based neural algorithmic reasoners (NARs). Such NARs proved effective as generic solvers for algorithmic tasks, when specified in graph form. To make their embeddings accessible to a Transformer, we propose a hybrid architecture with a two-phase training procedure, allowing the tokens in the language model to cross-attend to the node embeddings from the NAR. We evaluate our resulting TransNAR model on CLRS-Text, the text-based version of the CLRS-30 benchmark, and demonstrate significant gains over Transformer-only models for algorithmic reasoning, both in and out of distribution.

We present X-MDPT (Cross-view Masked Diffusion Prediction Transformers), a novel diffusion model designed for pose-guided human image generation. X-MDPT distinguishes itself by employing masked diffusion transformers that operate on latent patches, a departure from the commonly-used Unet structures in existing works. The model comprises three key modules: 1) a denoising diffusion Transformer, 2) an aggregation network that consolidates conditions into a single vector for the diffusion process, and 3) a mask cross-prediction module that enhances representation learning with semantic information from the reference image. X-MDPT demonstrates scalability, improving FID, SSIM, and LPIPS with larger models. Despite its simple design, our model outperforms state-of-the-art approaches on the DeepFashion dataset while exhibiting efficiency in terms of training parameters, training time, and inference speed. Our compact 33MB model achieves an FID of 7.42, surpassing a prior Unet latent diffusion approach (FID 8.07) using only 11times fewer parameters. Our best model surpasses the pixel-based diffusion with 2{3} of the parameters and achieves 5.43 times faster inference.

Despite the recent progress in speech emotion recognition (SER), state-of-the-art systems are unable to achieve improved performance in cross-language settings. In this paper, we propose a Multimodal Dual Attention Transformer (MDAT) model to improve cross-language SER. Our model utilises pre-trained models for multimodal feature extraction and is equipped with a dual attention mechanism including graph attention and co-attention to capture complex dependencies across different modalities and achieve improved cross-language SER results using minimal target language data. In addition, our model also exploits a transformer encoder layer for high-level feature representation to improve emotion classification accuracy. In this way, MDAT performs refinement of feature representation at various stages and provides emotional salient features to the classification layer. This novel approach also ensures the preservation of modality-specific emotional information while enhancing cross-modality and cross-language interactions. We assess our model's performance on four publicly available SER datasets and establish its superior effectiveness compared to recent approaches and baseline models.

Existing neural audio codecs usually sacrifice computational complexity for audio quality. They build the feature transformation layers mainly on convolutional blocks, which are not inherently appropriate for capturing local redundancies of audio signals. As compensation, either adversarial losses from a discriminator or a large number of model parameters are required to improve the codec. To that end, we propose Efficient Speech Codec (ESC), a lightweight parameter-efficient codec laid on cross-scale residual vector quantization and transformers. Our model leverages mirrored hierarchical window-attention transformer blocks and performs step-wise decoding from coarse-to-fine feature representations. To enhance codebook utilization, we design a learning paradigm that involves a pre-training stage to assist with codec training. Extensive results show that ESC can achieve high audio quality with much lower complexity, which is a prospective alternative in place of existing codecs.

We study the power of cross-attention in the Transformer architecture within the context of transfer learning for machine translation, and extend the findings of studies into cross-attention when training from scratch. We conduct a series of experiments through fine-tuning a translation model on data where either the source or target language has changed. These experiments reveal that fine-tuning only the cross-attention parameters is nearly as effective as fine-tuning all parameters (i.e., the entire translation model). We provide insights into why this is the case and observe that limiting fine-tuning in this manner yields cross-lingually aligned embeddings. The implications of this finding for researchers and practitioners include a mitigation of catastrophic forgetting, the potential for zero-shot translation, and the ability to extend machine translation models to several new language pairs with reduced parameter storage overhead.

Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a large variety of downstream audio tasks, such as real-time ASR and audio-call enhancement, a PSE solution should operate in a streaming mode, i.e., input audio cleaning should happen in real-time with a small latency and real-time factor. Personalisation is typically achieved by extracting a target speaker's voice profile from an enrolment audio, in the form of a static embedding vector, and then using it to condition the output of a PSE model. However, a fixed target speaker embedding may not be optimal under all conditions. In this work, we present a streaming Transformer-based PSE model and propose a novel cross-attention approach that gives adaptive target speaker representations. We present extensive experiments and show that our proposed cross-attention approach outperforms competitive baselines consistently, even when our model is only approximately half the size.

The extraction of aspect terms is a critical step in fine-grained sentiment analysis of text. Existing approaches for this task have yielded impressive results when the training and testing data are from the same domain. However, these methods show a drastic decrease in performance when applied to cross-domain settings where the domain of the testing data differs from that of the training data. To address this lack of extensibility and robustness, we propose a novel approach for automatically constructing domain-specific knowledge graphs that contain information relevant to the identification of aspect terms. We introduce a methodology for injecting information from these knowledge graphs into Transformer models, including two alternative mechanisms for knowledge insertion: via query enrichment and via manipulation of attention patterns. We demonstrate state-of-the-art performance on benchmark datasets for cross-domain aspect term extraction using our approach and investigate how the amount of external knowledge available to the Transformer impacts model performance.

Recently, multiple architectures has been proposed to improve the efficiency of the Transformer Language Models through changing the design of the self-attention block to have a linear-cost inference (LCI). A notable approach in this realm is the State-Space Machines (SSMs) architecture, which showed on-par performance on language modeling tasks with the self-attention transformers. However, such an architectural change requires a full pretraining of the weights from scratch, which incurs a huge cost to researchers and practitioners who want to use the new architectures. In the more traditional linear attention works, it has been proposed to approximate full attention with linear attention by swap-and-finetune framework. Motivated by this approach, we propose Cross-Architecture Transfer Learning (XATL), in which the weights of the shared components between LCI and self-attention-based transformers, such as layernorms, MLPs, input/output embeddings, are directly transferred to the new architecture from already pre-trained model parameters. We experimented the efficacy of the method on varying sizes and alternative attention architectures and show that \methodabbr significantly reduces the training time up to 2.5x times and converges to a better minimum with up to 2.6% stronger model on the LM benchmarks within the same compute budget.

Transformer encoder architectures have recently achieved state-of-the-art results on monocular 3D human mesh reconstruction, but they require a substantial number of parameters and expensive computations. Due to the large memory overhead and slow inference speed, it is difficult to deploy such models for practical use. In this paper, we propose a novel transformer encoder-decoder architecture for 3D human mesh reconstruction from a single image, called FastMETRO. We identify the performance bottleneck in the encoder-based transformers is caused by the token design which introduces high complexity interactions among input tokens. We disentangle the interactions via an encoder-decoder architecture, which allows our model to demand much fewer parameters and shorter inference time. In addition, we impose the prior knowledge of human body's morphological relationship via attention masking and mesh upsampling operations, which leads to faster convergence with higher accuracy. Our FastMETRO improves the Pareto-front of accuracy and efficiency, and clearly outperforms image-based methods on Human3.6M and 3DPW. Furthermore, we validate its generalizability on FreiHAND.

Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are equipped with the same type of sensors, which significantly hampers the scale of collaboration and benefit of cross-modality interactions. In this paper, we investigate the multi-agent hetero-modal cooperative perception problem where agents may have distinct sensor modalities. We present HM-ViT, the first unified multi-agent hetero-modal cooperative perception framework that can collaboratively predict 3D objects for highly dynamic vehicle-to-vehicle (V2V) collaborations with varying numbers and types of agents. To effectively fuse features from multi-view images and LiDAR point clouds, we design a novel heterogeneous 3D graph transformer to jointly reason inter-agent and intra-agent interactions. The extensive experiments on the V2V perception dataset OPV2V demonstrate that the HM-ViT outperforms SOTA cooperative perception methods for V2V hetero-modal cooperative perception. We will release codes to facilitate future research.

While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem. In this approach, a set of related images is generated simultaneously, optionally conditioned on a subset of the group. GDTs build upon diffusion transformers with minimal architectural modifications by concatenating self-attention tokens across images. This allows the model to implicitly capture cross-image relationships (e.g., identities, styles, layouts, surroundings, and color schemes) through caption-based correlations. Our design enables scalable, unsupervised, and task-agnostic pretraining using extensive collections of image groups sourced from multimodal internet articles, image galleries, and video frames. We evaluate GDTs on a comprehensive benchmark featuring over 200 instructions across 30 distinct visual generation tasks, including picture book creation, font design, style transfer, sketching, colorization, drawing sequence generation, and character customization. Our models achieve competitive zero-shot performance without any additional fine-tuning or gradient updates. Furthermore, ablation studies confirm the effectiveness of key components such as data scaling, group size, and model design. These results demonstrate the potential of GDTs as scalable, general-purpose visual generation systems.

Transformers have shown improved performance when compared to previous architectures for sequence processing such as RNNs. Despite their sizeable performance gains, as recently suggested, the model is computationally expensive to train and with a high parameter budget. In light of this, we explore parameter-sharing methods in Transformers with a specific focus on generative models. We perform an analysis of different parameter sharing/reduction methods and develop the Subformer. Our model combines sandwich-style parameter sharing, which overcomes naive cross-layer parameter sharing in generative models, and self-attentive embedding factorization (SAFE). Experiments on machine translation, abstractive summarization and language modeling show that the Subformer can outperform the Transformer even when using significantly fewer parameters.

Recent advancements in text-to-speech (TTS) powered by language models have showcased remarkable capabilities in achieving naturalness and zero-shot voice cloning. Notably, the decoder-only transformer is the prominent architecture in this domain. However, transformers face challenges stemming from their quadratic complexity in sequence length, impeding training on lengthy sequences and resource-constrained hardware. Moreover they lack specific inductive bias with regards to the monotonic nature of TTS alignments. In response, we propose to replace transformers with emerging recurrent architectures and introduce specialized cross-attention mechanisms for reducing repeating and skipping issues. Consequently our architecture can be efficiently trained on long samples and achieve state-of-the-art zero-shot voice cloning against baselines of comparable size. Our implementation and demos are available at https://github.com/theodorblackbird/lina-speech.

Deep learning for time series forecasting has traditionally operated within a one-model-per-dataset framework, limiting its potential to leverage the game-changing impact of large pre-trained models. The concept of universal forecasting, emerging from pre-training on a vast collection of time series datasets, envisions a single Large Time Series Model capable of addressing diverse downstream forecasting tasks. However, constructing such a model poses unique challenges specific to time series data: i) cross-frequency learning, ii) accommodating an arbitrary number of variates for multivariate time series, and iii) addressing the varying distributional properties inherent in large-scale data. To address these challenges, we present novel enhancements to the conventional time series Transformer architecture, resulting in our proposed Masked Encoder-based Universal Time Series Forecasting Transformer (Moirai). Trained on our newly introduced Large-scale Open Time Series Archive (LOTSA) featuring over 27B observations across nine domains, Moirai achieves competitive or superior performance as a zero-shot forecaster when compared to full-shot models. Code, model weights, and data will be released.

Non-hierarchical sparse attention Transformer-based models, such as Longformer and Big Bird, are popular approaches to working with long documents. There are clear benefits to these approaches compared to the original Transformer in terms of efficiency, but Hierarchical Attention Transformer (HAT) models are a vastly understudied alternative. We develop and release fully pre-trained HAT models that use segment-wise followed by cross-segment encoders and compare them with Longformer models and partially pre-trained HATs. In several long document downstream classification tasks, our best HAT model outperforms equally-sized Longformer models while using 10-20% less GPU memory and processing documents 40-45% faster. In a series of ablation studies, we find that HATs perform best with cross-segment contextualization throughout the model than alternative configurations that implement either early or late cross-segment contextualization. Our code is on GitHub: https://github.com/coastalcph/hierarchical-transformers.

Enterprise documents such as forms, invoices, receipts, reports, contracts, and other similar records, often carry rich semantics at the intersection of textual and spatial modalities. The visual cues offered by their complex layouts play a crucial role in comprehending these documents effectively. In this paper, we present DocLLM, a lightweight extension to traditional large language models (LLMs) for reasoning over visual documents, taking into account both textual semantics and spatial layout. Our model differs from existing multimodal LLMs by avoiding expensive image encoders and focuses exclusively on bounding box information to incorporate the spatial layout structure. Specifically, the cross-alignment between text and spatial modalities is captured by decomposing the attention mechanism in classical transformers to a set of disentangled matrices. Furthermore, we devise a pre-training objective that learns to infill text segments. This approach allows us to address irregular layouts and heterogeneous content frequently encountered in visual documents. The pre-trained model is fine-tuned using a large-scale instruction dataset, covering four core document intelligence tasks. We demonstrate that our solution outperforms SotA LLMs on 14 out of 16 datasets across all tasks, and generalizes well to 4 out of 5 previously unseen datasets.

We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0.3B upto 8B parameters on datasets up to 600M images. We find that U-ViT, a pure self-attention based DiT model provides a simpler design and scales more effectively in comparison with cross-attention based DiT variants, which allows straightforward expansion for extra conditions and other modalities. We identify a 2.3B U-ViT model can get better performance than SDXL UNet and other DiT variants in controlled setting. On the data scaling side, we investigate how increasing dataset size and enhanced long caption improve the text-image alignment performance and the learning efficiency.

We present a novel approach for the detection of deepfake videos using a pair of vision transformers pre-trained by a self-supervised masked autoencoding setup. Our method consists of two distinct components, one of which focuses on learning spatial information from individual RGB frames of the video, while the other learns temporal consistency information from optical flow fields generated from consecutive frames. Unlike most approaches where pre-training is performed on a generic large corpus of images, we show that by pre-training on smaller face-related datasets, namely Celeb-A (for the spatial learning component) and YouTube Faces (for the temporal learning component), strong results can be obtained. We perform various experiments to evaluate the performance of our method on commonly used datasets namely FaceForensics++ (Low Quality and High Quality, along with a new highly compressed version named Very Low Quality) and Celeb-DFv2 datasets. Our experiments show that our method sets a new state-of-the-art on FaceForensics++ (LQ, HQ, and VLQ), and obtains competitive results on Celeb-DFv2. Moreover, our method outperforms other methods in the area in a cross-dataset setup where we fine-tune our model on FaceForensics++ and test on CelebDFv2, pointing to its strong cross-dataset generalization ability.

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text translation via semantic knowledge distillation. We show that by initializing the encoder of the encoder-decoder sequence-to-sequence translation model with SAMU-XLS-R, a multilingual speech transformer encoder trained using multi-modal (speech-text) semantic knowledge distillation, we achieve significantly better cross-lingual task knowledge transfer than the baseline XLS-R, a multilingual speech transformer encoder trained via self-supervised learning. We demonstrate the effectiveness of our approach on two popular datasets, namely, CoVoST-2 and Europarl. On the 21 translation tasks of the CoVoST-2 benchmark, we achieve an average improvement of 12.8 BLEU points over the baselines. In the zero-shot translation scenario, we achieve an average gain of 18.8 and 11.9 average BLEU points on unseen medium and low-resource languages. We make similar observations on Europarl speech translation benchmark.

Today, the acquisition of various behavioral log data has enabled deeper understanding of customer preferences and future behaviors in the marketing field. In particular, multimodal deep learning has achieved highly accurate predictions by combining multiple types of data. Many of these studies utilize with feature fusion to construct multimodal models, which combines extracted representations from each modality. However, since feature fusion treats information from each modality equally, it is difficult to perform flexible analysis such as the attention mechanism that has been used extensively in recent years. Therefore, this study proposes a context-aware multimodal deep learning model that combines Bidirectional Encoder Representations from Transformers (BERT) and cross-attention Transformer, which dynamically changes the attention of deep-contextualized word representations based on background information such as consumer demographic and lifestyle variables. We conduct a comprehensive analysis and demonstrate the effectiveness of our model by comparing it with six reference models in three categories using behavioral logs stored on an online platform. In addition, we present an efficient multimodal learning method by comparing the learning efficiency depending on the optimizers and the prediction accuracy depending on the number of tokens in the text data.

Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually important to visual inputs. The reasons are two-fold: (1) Input embeddings of each layer are equal-scale, so no cross-scale feature can be extracted; (2) to lower the computational cost, some vision transformers merge adjacent embeddings inside the self-attention module, thus sacrificing small-scale (fine-grained) features of the embeddings and also disabling the cross-scale interactions. To this end, we propose Cross-scale Embedding Layer (CEL) and Long Short Distance Attention (LSDA). On the one hand, CEL blends each embedding with multiple patches of different scales, providing the self-attention module itself with cross-scale features. On the other hand, LSDA splits the self-attention module into a short-distance one and a long-distance counterpart, which not only reduces the computational burden but also keeps both small-scale and large-scale features in the embeddings. Through the above two designs, we achieve cross-scale attention. Besides, we put forward a dynamic position bias for vision transformers to make the popular relative position bias apply to variable-sized images. Hinging on the cross-scale attention module, we construct a versatile vision architecture, dubbed CrossFormer, which accommodates variable-sized inputs. Extensive experiments show that CrossFormer outperforms the other vision transformers on image classification, object detection, instance segmentation, and semantic segmentation tasks. The code has been released: https://github.com/cheerss/CrossFormer.

Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model by inserting cross-attention into the image and text backbones, bringing gains in terms of memory and performance. In addition, unlike previous work that is either only pre-trained on image-text data or on fine-grained data with box-level annotations, we present a two-stage pre-training strategy that uses both these kinds of data efficiently: (i) coarse-grained pre-training based on image-text data; followed by (ii) fine-grained pre-training based on image-text-box data. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection. Using deep multimodal fusion coupled with the two-stage pre-training, FIBER provides consistent performance improvements over strong baselines across all tasks, often outperforming methods using magnitudes more data. Code is available at https://github.com/microsoft/FIBER.

In recent times there has been a surge of multi-modal architectures based on Large Language Models, which leverage the zero shot generation capabilities of LLMs and project image embeddings into the text space and then use the auto-regressive capacity to solve tasks such as VQA, captioning, and image retrieval. We name these architectures as "bridge-architectures" as they project from the image space to the text space. These models deviate from the traditional recipe of training transformer based multi-modal models, which involve using large-scale pre-training and complex multi-modal interactions through co or cross attention. However, the capabilities of bridge architectures have not been tested on complex visual reasoning tasks which require fine grained analysis about the image. In this project, we investigate the performance of these bridge-architectures on the NLVR2 dataset, and compare it to state-of-the-art transformer based architectures. We first extend the traditional bridge architectures for the NLVR2 dataset, by adding object level features to faciliate fine-grained object reasoning. Our analysis shows that adding object level features to bridge architectures does not help, and that pre-training on multi-modal data is key for good performance on complex reasoning tasks such as NLVR2. We also demonstrate some initial results on a recently bridge-architecture, LLaVA, in the zero shot setting and analyze its performance.

The advent of the Transformer has led to the development of large language models (LLM), which appear to demonstrate human-like capabilities. To assess the generality of this class of models and a variety of other base neural network architectures to multimodal domains, we evaluated and compared their capacity for multimodal generalization. We introduce a multimodal question-answer benchmark to evaluate three specific types of out-of-distribution (OOD) generalization performance: distractor generalization (generalization in the presence of distractors), systematic compositional generalization (generalization to new task permutations), and productive compositional generalization (generalization to more complex tasks structures). We found that across model architectures (e.g., RNNs, Transformers, Perceivers, etc.), models with multiple attention layers, or models that leveraged cross-attention mechanisms between input domains, fared better. Our positive results demonstrate that for multimodal distractor and systematic generalization, either cross-modal attention or models with deeper attention layers are key architectural features required to integrate multimodal inputs. On the other hand, neither of these architectural features led to productive generalization, suggesting fundamental limitations of existing architectures for specific types of multimodal generalization. These results demonstrate the strengths and limitations of specific architectural components underlying modern neural models for multimodal reasoning. Finally, we provide Generic COG (gCOG), a configurable benchmark with several multimodal generalization splits, for future studies to explore.

With the recent success of the pre-training technique for NLP and image-linguistic tasks, some video-linguistic pre-training works are gradually developed to improve video-text related downstream tasks. However, most of the existing multimodal models are pre-trained for understanding tasks, leading to a pretrain-finetune discrepancy for generation tasks. This paper proposes UniVL: a Unified Video and Language pre-training model for both multimodal understanding and generation. It comprises four components, including two single-modal encoders, a cross encoder, and a decoder with the Transformer backbone. Five objectives, including video-text joint, conditioned masked language model (CMLM), conditioned masked frame model (CMFM), video-text alignment, and language reconstruction, are designed to train each of the components. We further develop two pre-training strategies, stage by stage pre-training (StagedP) and enhanced video representation (EnhancedV), to make the training process of the UniVL more effective. The pre-train is carried out on a sizeable instructional video dataset HowTo100M. Experimental results demonstrate that the UniVL can learn strong video-text representation and achieves state-of-the-art results on five downstream tasks.

While there has been a large body of research attempting to circumvent tokenization for language modeling (Clark et al., 2022; Xue et al., 2022), the current consensus is that it is a necessary initial step for designing state-of-the-art performant language models. In this paper, we investigate tokenization from a theoretical point of view by studying the behavior of transformers on simple data generating processes. When trained on data drawn from certain simple k^{th}-order Markov processes for k > 1, transformers exhibit a surprising phenomenon - in the absence of tokenization, they empirically fail to learn the right distribution and predict characters according to a unigram model (Makkuva et al., 2024). With the addition of tokenization, however, we empirically observe that transformers break through this barrier and are able to model the probabilities of sequences drawn from the source near-optimally, achieving small cross-entropy loss. With this observation as starting point, we study the end-to-end cross-entropy loss achieved by transformers with and without tokenization. With the appropriate tokenization, we show that even the simplest unigram models (over tokens) learnt by transformers are able to model the probability of sequences drawn from k^{th}-order Markov sources near optimally. Our analysis provides a justification for the use of tokenization in practice through studying the behavior of transformers on Markovian data.

Cross-modal alignment Learning integrates information from different modalities like text, image, audio and video to create unified models. This approach develops shared representations and learns correlations between modalities, enabling applications such as visual question answering and audiovisual content analysis. Current techniques rely on large modality-specific encoders, necessitating fine-tuning or training from scratch on vast aligned datasets (e.g., text-image, text-audio, image-audio). This approach has limitations: (i) it is very expensive due to the need for training large encoders on extensive datasets, (ii) acquiring aligned large paired datasets is challenging, and (iii) adding new modalities requires retraining the entire framework to incorporate these modalities. To address these issues, we propose OneEncoder, a lightweight framework that progressively represents and aligns four modalities (image, text, audio, video). Initially, we train a lightweight Universal Projection module (UP) to align image and text modalities. Then, we freeze the pretrained UP and progressively align future modalities to those already aligned. OneEncoder operates efficiently and cost-effectively, even in scenarios where vast aligned datasets are unavailable, due to its lightweight design. Trained on small paired datasets, it shows strong performance in tasks like classification, querying, and visual question answering, surpassing methods that rely on large datasets and specialized encoders.

Diffusion models, and their generalization, flow matching, have had a remarkable impact on the field of media generation. Here, the conventional approach is to learn the complex mapping from a simple source distribution of Gaussian noise to the target media distribution. For cross-modal tasks such as text-to-image generation, this same mapping from noise to image is learnt whilst including a conditioning mechanism in the model. One key and thus far relatively unexplored feature of flow matching is that, unlike Diffusion models, they are not constrained for the source distribution to be noise. Hence, in this paper, we propose a paradigm shift, and ask the question of whether we can instead train flow matching models to learn a direct mapping from the distribution of one modality to the distribution of another, thus obviating the need for both the noise distribution and conditioning mechanism. We present a general and simple framework, CrossFlow, for cross-modal flow matching. We show the importance of applying Variational Encoders to the input data, and introduce a method to enable Classifier-free guidance. Surprisingly, for text-to-image, CrossFlow with a vanilla transformer without cross attention slightly outperforms standard flow matching, and we show that it scales better with training steps and model size, while also allowing for interesting latent arithmetic which results in semantically meaningful edits in the output space. To demonstrate the generalizability of our approach, we also show that CrossFlow is on par with or outperforms the state-of-the-art for various cross-modal / intra-modal mapping tasks, viz. image captioning, depth estimation, and image super-resolution. We hope this paper contributes to accelerating progress in cross-modal media generation.

A big convergence of language, vision, and multimodal pretraining is emerging. In this work, we introduce a general-purpose multimodal foundation model BEiT-3, which achieves state-of-the-art transfer performance on both vision and vision-language tasks. Specifically, we advance the big convergence from three aspects: backbone architecture, pretraining task, and model scaling up. We introduce Multiway Transformers for general-purpose modeling, where the modular architecture enables both deep fusion and modality-specific encoding. Based on the shared backbone, we perform masked "language" modeling on images (Imglish), texts (English), and image-text pairs ("parallel sentences") in a unified manner. Experimental results show that BEiT-3 obtains state-of-the-art performance on object detection (COCO), semantic segmentation (ADE20K), image classification (ImageNet), visual reasoning (NLVR2), visual question answering (VQAv2), image captioning (COCO), and cross-modal retrieval (Flickr30K, COCO).

Attention-based models are appealing for multimodal processing because inputs from multiple modalities can be concatenated and fed to a single backbone network - thus requiring very little fusion engineering. The resulting representations are however fully entangled throughout the network, which may not always be desirable: in learning, contrastive audio-visual self-supervised learning requires independent audio and visual features to operate, otherwise learning collapses; in inference, evaluation of audio-visual models should be possible on benchmarks having just audio or just video. In this paper, we introduce Zorro, a technique that uses masks to control how inputs from each modality are routed inside Transformers, keeping some parts of the representation modality-pure. We apply this technique to three popular transformer-based architectures (ViT, Swin and HiP) and show that with contrastive pre-training Zorro achieves state-of-the-art results on most relevant benchmarks for multimodal tasks (AudioSet and VGGSound). Furthermore, the resulting models are able to perform unimodal inference on both video and audio benchmarks such as Kinetics-400 or ESC-50.

Integrating multiple generative foundation models, especially those trained on different modalities, into something greater than the sum of its parts poses significant challenges. Two key hurdles are the availability of aligned data (concepts that contain similar meaning but is expressed differently in different modalities), and effectively leveraging unimodal representations in cross-domain generative tasks, without compromising their original unimodal capabilities. We propose Zipper, a multi-tower decoder architecture that addresses these concerns by using cross-attention to flexibly compose multimodal generative models from independently pre-trained unimodal decoders. In our experiments fusing speech and text modalities, we show the proposed architecture performs very competitively in scenarios with limited aligned text-speech data. We also showcase the flexibility of our model to selectively maintain unimodal (e.g., text-to-text generation) generation performance by freezing the corresponding modal tower (e.g. text). In cross-modal tasks such as automatic speech recognition (ASR) where the output modality is text, we show that freezing the text backbone results in negligible performance degradation. In cross-modal tasks such as text-to-speech generation (TTS) where the output modality is speech, we show that using a pre-trained speech backbone results in superior performance to the baseline.

Vision-Language (VL) models with the Two-Tower architecture have dominated visual-language representation learning in recent years. Current VL models either use lightweight uni-modal encoders and learn to extract, align and fuse both modalities simultaneously in a deep cross-modal encoder, or feed the last-layer uni-modal representations from the deep pre-trained uni-modal encoders into the top cross-modal encoder. Both approaches potentially restrict vision-language representation learning and limit model performance. In this paper, we propose BridgeTower, which introduces multiple bridge layers that build a connection between the top layers of uni-modal encoders and each layer of the cross-modal encoder. This enables effective bottom-up cross-modal alignment and fusion between visual and textual representations of different semantic levels of pre-trained uni-modal encoders in the cross-modal encoder. Pre-trained with only 4M images, BridgeTower achieves state-of-the-art performance on various downstream vision-language tasks. In particular, on the VQAv2 test-std set, BridgeTower achieves an accuracy of 78.73%, outperforming the previous state-of-the-art model METER by 1.09% with the same pre-training data and almost negligible additional parameters and computational costs. Notably, when further scaling the model, BridgeTower achieves an accuracy of 81.15%, surpassing models that are pre-trained on orders-of-magnitude larger datasets. Code and checkpoints are available at https://github.com/microsoft/BridgeTower.

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention mechanisms. These attention modules also play a role in other computer vision tasks including object detection and image segmentation. Unlike Transformers that only use self-attention, Transformers with co-attention require to consider multiple attention maps in parallel in order to highlight the information that is relevant to the prediction in the model's input. In this work, we propose the first method to explain prediction by any Transformer-based architecture, including bi-modal Transformers and Transformers with co-attentions. We provide generic solutions and apply these to the three most commonly used of these architectures: (i) pure self-attention, (ii) self-attention combined with co-attention, and (iii) encoder-decoder attention. We show that our method is superior to all existing methods which are adapted from single modality explainability.

Joint audio-video (AV) generation is still a significant challenge in generative AI, primarily due to three critical requirements: quality of the generated samples, seamless multimodal synchronization and temporal coherence, with audio tracks that match the visual data and vice versa, and limitless video duration. In this paper, we present , a novel transformer-based architecture that addresses all the key challenges of AV generation. We explore three distinct cross modality interaction modules, with our lightweight temporal fusion module emerging as the most effective and computationally efficient approach for aligning audio and visual modalities. Our experimental results demonstrate that outperforms existing state-of-the-art models in multimodal AV generation tasks. Our code and checkpoints are available at https://github.com/ErgastiAlex/R-FLAV.

The robustness of multimodal deep learning models to realistic changes in the input text is critical for their applicability to important tasks such as text-to-image retrieval and cross-modal entailment. To measure robustness, several existing approaches edit the text data, but do so without leveraging the cross-modal information present in multimodal data. Information from the visual modality, such as color, size, and shape, provide additional attributes that users can include in their inputs. Thus, we propose cross-modal attribute insertions as a realistic perturbation strategy for vision-and-language data that inserts visual attributes of the objects in the image into the corresponding text (e.g., "girl on a chair" to "little girl on a wooden chair"). Our proposed approach for cross-modal attribute insertions is modular, controllable, and task-agnostic. We find that augmenting input text using cross-modal insertions causes state-of-the-art approaches for text-to-image retrieval and cross-modal entailment to perform poorly, resulting in relative drops of 15% in MRR and 20% in F_1 score, respectively. Crowd-sourced annotations demonstrate that cross-modal insertions lead to higher quality augmentations for multimodal data than augmentations using text-only data, and are equivalent in quality to original examples. We release the code to encourage robustness evaluations of deep vision-and-language models: https://github.com/claws-lab/multimodal-robustness-xmai.

Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.

Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging to design a unified network for processing various modalities (e.g. natural language, 2D images, 3D point clouds, audio, video, time series, tabular data) due to the inherent gaps among them. In this work, we propose a framework, named Meta-Transformer, that leverages a frozen encoder to perform multimodal perception without any paired multimodal training data. In Meta-Transformer, the raw input data from various modalities are mapped into a shared token space, allowing a subsequent encoder with frozen parameters to extract high-level semantic features of the input data. Composed of three main components: a unified data tokenizer, a modality-shared encoder, and task-specific heads for downstream tasks, Meta-Transformer is the first framework to perform unified learning across 12 modalities with unpaired data. Experiments on different benchmarks reveal that Meta-Transformer can handle a wide range of tasks including fundamental perception (text, image, point cloud, audio, video), practical application (X-Ray, infrared, hyperspectral, and IMU), and data mining (graph, tabular, and time-series). Meta-Transformer indicates a promising future for developing unified multimodal intelligence with transformers. Code will be available at https://github.com/invictus717/MetaTransformer

Existing top-performance autonomous driving systems typically rely on the multi-modal fusion strategy for reliable scene understanding. This design is however fundamentally restricted due to overlooking the modality-specific strengths and finally hampering the model performance. To address this limitation, in this work, we introduce a novel modality interaction strategy that allows individual per-modality representations to be learned and maintained throughout, enabling their unique characteristics to be exploited during the whole perception pipeline. To demonstrate the effectiveness of the proposed strategy, we design DeepInteraction++, a multi-modal interaction framework characterized by a multi-modal representational interaction encoder and a multi-modal predictive interaction decoder. Specifically, the encoder is implemented as a dual-stream Transformer with specialized attention operation for information exchange and integration between separate modality-specific representations. Our multi-modal representational learning incorporates both object-centric, precise sampling-based feature alignment and global dense information spreading, essential for the more challenging planning task. The decoder is designed to iteratively refine the predictions by alternately aggregating information from separate representations in a unified modality-agnostic manner, realizing multi-modal predictive interaction. Extensive experiments demonstrate the superior performance of the proposed framework on both 3D object detection and end-to-end autonomous driving tasks. Our code is available at https://github.com/fudan-zvg/DeepInteraction.

We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder that requires both modalities, limiting their use for retrieval-style end tasks or more complex multitask learning with two unimodal encoders, limiting early cross-modal fusion. We instead introduce new pretraining masking schemes that better mix across modalities (e.g. by forcing masks for text to predict the closest video embeddings) while also maintaining separability (e.g. unimodal predictions are sometimes required, without using all the input). Experimental results show strong performance across a wider range of tasks than any previous methods, often outperforming task-specific pre-training. Code is made available at https://github.com/pytorch/fairseq/tree/main/examples/MMPT.

Mainstream Video-Language Pre-training models actbert,clipbert,violet consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end video-language model, namely all-in-one Transformer, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified backbone model. Our pre-trained all-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and visual commonsense reasoning. State-of-the-art performances with the minimal model FLOPs on nine datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained model have been released in https://github.com/showlab/all-in-one.

We present Vx2Text, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio. In order to leverage transformer networks, which have been shown to be effective at modeling language, each modality is first converted into a set of language embeddings by a learnable tokenizer. This allows our approach to perform multimodal fusion in the language space, thus eliminating the need for ad-hoc cross-modal fusion modules. To address the non-differentiability of tokenization on continuous inputs (e.g., video or audio), we utilize a relaxation scheme that enables end-to-end training. Furthermore, unlike prior encoder-only models, our network includes an autoregressive decoder to generate open-ended text from the multimodal embeddings fused by the language encoder. This renders our approach fully generative and makes it directly applicable to different "video+x to text" problems without the need to design specialized network heads for each task. The proposed framework is not only conceptually simple but also remarkably effective: experiments demonstrate that our approach based on a single architecture outperforms the state-of-the-art on three video-based text-generation tasks -- captioning, question answering and audio-visual scene-aware dialog.

Current machine learning models for vision are often highly specialized and limited to a single modality and task. In contrast, recent large language models exhibit a wide range of capabilities, hinting at a possibility for similarly versatile models in computer vision. In this paper, we take a step in this direction and propose a multimodal training scheme called 4M. It consists of training a single unified Transformer encoder-decoder using a masked modeling objective across a wide range of input/output modalities - including text, images, geometric, and semantic modalities, as well as neural network feature maps. 4M achieves scalability by unifying the representation space of all modalities through mapping them into discrete tokens and performing multimodal masked modeling on a small randomized subset of tokens. 4M leads to models that exhibit several key capabilities: (1) they can perform a diverse set of vision tasks out of the box, (2) they excel when fine-tuned for unseen downstream tasks or new input modalities, and (3) they can function as a generative model that can be conditioned on arbitrary modalities, enabling a wide variety of expressive multimodal editing capabilities with remarkable flexibility. Through experimental analyses, we demonstrate the potential of 4M for training versatile and scalable foundation models for vision tasks, setting the stage for further exploration in multimodal learning for vision and other domains.

We propose and investigate an identity sensitive joint embedding of face and voice. Such an embedding enables cross-modal retrieval from voice to face and from face to voice. We make the following four contributions: first, we show that the embedding can be learnt from videos of talking faces, without requiring any identity labels, using a form of cross-modal self-supervision; second, we develop a curriculum learning schedule for hard negative mining targeted to this task, that is essential for learning to proceed successfully; third, we demonstrate and evaluate cross-modal retrieval for identities unseen and unheard during training over a number of scenarios and establish a benchmark for this novel task; finally, we show an application of using the joint embedding for automatically retrieving and labelling characters in TV dramas.

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes unsustainable due to heavy computational and storage costs. This paper proposes UniAdapter, which unifies unimodal and multimodal adapters for parameter-efficient cross-modal adaptation on pre-trained vision-language models. Specifically, adapters are distributed to different modalities and their interactions, with the total number of tunable parameters reduced by partial weight sharing. The unified and knowledge-sharing design enables powerful cross-modal representations that can benefit various downstream tasks, requiring only 1.0%-2.0% tunable parameters of the pre-trained model. Extensive experiments on 6 cross-modal downstream benchmarks (including video-text retrieval, image-text retrieval, VideoQA, and VQA) show that in most cases, UniAdapter not only outperforms the state-of-the-arts, but even beats the full fine-tuning strategy. Particularly, on the MSRVTT retrieval task, UniAdapter achieves 49.7% recall@1 with 2.2% model parameters, outperforming the latest competitors by 2.0%. The code and models are available at https://github.com/RERV/UniAdapter.

The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational resources compared to text-only LLMs. To address the scaling challenges, we introduce Mixture-of-Transformers (MoT), a sparse multi-modal transformer architecture that significantly reduces pretraining computational costs. MoT decouples non-embedding parameters of the model by modality -- including feed-forward networks, attention matrices, and layer normalization -- enabling modality-specific processing with global self-attention over the full input sequence. We evaluate MoT across multiple settings and model scales. In the Chameleon 7B setting (autoregressive text-and-image generation), MoT matches the dense baseline's performance using only 55.8\% of the FLOPs. When extended to include speech, MoT reaches speech performance comparable to the dense baseline with only 37.2\% of the FLOPs. In the Transfusion setting, where text and image are trained with different objectives, a 7B MoT model matches the image modality performance of the dense baseline with one third of the FLOPs, and a 760M MoT model outperforms a 1.4B dense baseline across key image generation metrics. System profiling further highlights MoT's practical benefits, achieving dense baseline image quality in 47.2\% of the wall-clock time and text quality in 75.6\% of the wall-clock time (measured on AWS p4de.24xlarge instances with NVIDIA A100 GPUs).

The ability to quickly learn a new task with minimal instruction - known as few-shot learning - is a central aspect of intelligent agents. Classical few-shot benchmarks make use of few-shot samples from a single modality, but such samples may not be sufficient to characterize an entire concept class. In contrast, humans use cross-modal information to learn new concepts efficiently. In this work, we demonstrate that one can indeed build a better {bf visual} dog classifier by {bf read}ing about dogs and {bf listen}ing to them bark. To do so, we exploit the fact that recent multimodal foundation models such as CLIP are inherently cross-modal, mapping different modalities to the same representation space. Specifically, we propose a simple cross-modal adaptation approach that learns from few-shot examples spanning different modalities. By repurposing class names as additional one-shot training samples, we achieve SOTA results with an embarrassingly simple linear classifier for vision-language adaptation. Furthermore, we show that our approach can benefit existing methods such as prefix tuning, adapters, and classifier ensembling. Finally, to explore other modalities beyond vision and language, we construct the first (to our knowledge) audiovisual few-shot benchmark and use cross-modal training to improve the performance of both image and audio classification.

We abstract the features (i.e. learned representations) of multi-modal data into 1) uni-modal features, which can be learned from uni-modal training, and 2) paired features, which can only be learned from cross-modal interactions. Multi-modal models are expected to benefit from cross-modal interactions on the basis of ensuring uni-modal feature learning. However, recent supervised multi-modal late-fusion training approaches still suffer from insufficient learning of uni-modal features on each modality. We prove that this phenomenon does hurt the model's generalization ability. To this end, we propose to choose a targeted late-fusion learning method for the given supervised multi-modal task from Uni-Modal Ensemble(UME) and the proposed Uni-Modal Teacher(UMT), according to the distribution of uni-modal and paired features. We demonstrate that, under a simple guiding strategy, we can achieve comparable results to other complex late-fusion or intermediate-fusion methods on various multi-modal datasets, including VGG-Sound, Kinetics-400, UCF101, and ModelNet40.

We introduce X-VILA, an omni-modality model designed to extend the capabilities of large language models (LLMs) by incorporating image, video, and audio modalities. By aligning modality-specific encoders with LLM inputs and diffusion decoders with LLM outputs, X-VILA achieves cross-modality understanding, reasoning, and generation. To facilitate this cross-modality alignment, we curate an effective interleaved any-to-any modality instruction-following dataset. Furthermore, we identify a significant problem with the current cross-modality alignment method, which results in visual information loss. To address the issue, we propose a visual alignment mechanism with a visual embedding highway module. We then introduce a resource-efficient recipe for training X-VILA, that exhibits proficiency in any-to-any modality conversation, surpassing previous approaches by large margins. X-VILA also showcases emergent properties across modalities even in the absence of similar training data. The project will be made open-source.

In recent years, with the realistic generation results and a wide range of personalized applications, diffusion-based generative models gain huge attention in both visual and audio generation areas. Compared to the considerable advancements of text2image or text2audio generation, research in audio2visual or visual2audio generation has been relatively slow. The recent audio-visual generation methods usually resort to huge large language model or composable diffusion models. Instead of designing another giant model for audio-visual generation, in this paper we take a step back showing a simple and lightweight generative transformer, which is not fully investigated in multi-modal generation, can achieve excellent results on image2audio generation. The transformer operates in the discrete audio and visual Vector-Quantized GAN space, and is trained in the mask denoising manner. After training, the classifier-free guidance could be deployed off-the-shelf achieving better performance, without any extra training or modification. Since the transformer model is modality symmetrical, it could also be directly deployed for audio2image generation and co-generation. In the experiments, we show that our simple method surpasses recent image2audio generation methods. Generated audio samples can be found at https://docs.google.com/presentation/d/1ZtC0SeblKkut4XJcRaDsSTuCRIXB3ypxmSi7HTY3IyQ

Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, e.g., Transformers, have attracted the attention of researchers to model compression. However, how to compress multimodal models, especially vison-language Transformers, is still under-explored. This paper proposes the Unified and Progressive Pruning (\emph{UPop}) as a universal vison-language Transformer compression framework, which incorporates 1) unifiedly searching multimodal subnets in a continuous optimization space from the original model, which enables automatic assignment of pruning ratios among compressible modalities and structures; 2) progressively searching and retraining the subnet, which maintains convergence between the search and retrain to attain higher compression ratios. Experiments on various tasks, datasets, and model architectures demonstrate the effectiveness and versatility of the proposed UPop framework. The code is available at https://github.com/sdc17/UPop.

How does audio describe the world around us? In this work, we propose a method for generating images of visual scenes from diverse in-the-wild sounds. This cross-modal generation task is challenging due to the significant information gap between auditory and visual signals. We address this challenge by designing a model that aligns audio-visual modalities by enriching audio features with visual information and translating them into the visual latent space. These features are then fed into the pre-trained image generator to produce images. To enhance image quality, we use sound source localization to select audio-visual pairs with strong cross-modal correlations. Our method achieves substantially better results on the VEGAS and VGGSound datasets compared to previous work and demonstrates control over the generation process through simple manipulations to the input waveform or latent space. Furthermore, we analyze the geometric properties of the learned embedding space and demonstrate that our learning approach effectively aligns audio-visual signals for cross-modal generation. Based on this analysis, we show that our method is agnostic to specific design choices, showing its generalizability by integrating various model architectures and different types of audio-visual data.

We present a unified Vision-Language pretrained Model (VLMo) that jointly learns a dual encoder and a fusion encoder with a modular Transformer network. Specifically, we introduce Mixture-of-Modality-Experts (MoME) Transformer, where each block contains a pool of modality-specific experts and a shared self-attention layer. Because of the modeling flexibility of MoME, pretrained VLMo can be fine-tuned as a fusion encoder for vision-language classification tasks, or used as a dual encoder for efficient image-text retrieval. Moreover, we propose a stagewise pre-training strategy, which effectively leverages large-scale image-only and text-only data besides image-text pairs. Experimental results show that VLMo achieves state-of-the-art results on various vision-language tasks, including VQA, NLVR2 and image-text retrieval. The code and pretrained models are available at https://aka.ms/vlmo.

Large foundation models have recently emerged as a prominent focus of interest, attaining superior performance in widespread scenarios. Due to the scarcity of 3D data, many efforts have been made to adapt pre-trained transformers from vision to 3D domains. However, such 2D-to-3D approaches are still limited, due to the potential loss of spatial geometries and high computation cost. More importantly, their frameworks are mainly designed for 2D models, lacking a general any-to-3D paradigm. In this paper, we introduce Any2Point, a parameter-efficient method to empower any-modality large models (vision, language, audio) for 3D understanding. Given a frozen transformer from any source modality, we propose a 3D-to-any (1D or 2D) virtual projection strategy that correlates the input 3D points to the original 1D or 2D positions within the source modality. This mechanism enables us to assign each 3D token with a positional encoding paired with the pre-trained model, which avoids 3D geometry loss caused by the true projection and better motivates the transformer for 3D learning with 1D/2D positional priors. Then, within each transformer block, we insert an any-to-3D guided adapter module for parameter-efficient fine-tuning. The adapter incorporates prior spatial knowledge from the source modality to guide the local feature aggregation of 3D tokens, compelling the semantic adaption of any-modality transformers. We conduct extensive experiments to showcase the effectiveness and efficiency of our method. Code and models are released at https://github.com/Ivan-Tang-3D/Any2Point.

Recently, the rise of large-scale vision-language pretrained models like CLIP, coupled with the technology of Parameter-Efficient FineTuning (PEFT), has captured substantial attraction in video action recognition. Nevertheless, prevailing approaches tend to prioritize strong supervised performance at the expense of compromising the models' generalization capabilities during transfer. In this paper, we introduce a novel Multimodal, Multi-task CLIP adapting framework named \name to address these challenges, preserving both high supervised performance and robust transferability. Firstly, to enhance the individual modality architectures, we introduce multimodal adapters to both the visual and text branches. Specifically, we design a novel visual TED-Adapter, that performs global Temporal Enhancement and local temporal Difference modeling to improve the temporal representation capabilities of the visual encoder. Moreover, we adopt text encoder adapters to strengthen the learning of semantic label information. Secondly, we design a multi-task decoder with a rich set of supervisory signals to adeptly satisfy the need for strong supervised performance and generalization within a multimodal framework. Experimental results validate the efficacy of our approach, demonstrating exceptional performance in supervised learning while maintaining strong generalization in zero-shot scenarios.

In this paper, we introduce a novel Multi-Modal Contrastive Pre-training Framework that synergistically combines X-rays, electrocardiograms (ECGs), and radiology/cardiology reports. Our approach leverages transformers to encode these diverse modalities into a unified representation space, aiming to enhance diagnostic accuracy and facilitate comprehensive patient assessments. We utilize LoRA-Peft to significantly reduce trainable parameters in the LLM and incorporate recent linear attention dropping strategy in the Vision Transformer(ViT) for smoother attention. Furthermore, we provide novel multimodal attention explanations and retrieval for our model. To the best of our knowledge, we are the first to propose an integrated model that combines X-ray, ECG, and Radiology/Cardiology Report with this approach. By utilizing contrastive loss, MoRE effectively aligns modality-specific features into a coherent embedding, which supports various downstream tasks such as zero-shot classification and multimodal retrieval. Employing our proposed methodology, we achieve state-of-the-art (SOTA) on the Mimic-IV, CheXpert, Edema Severity, and PtbXl downstream datasets, surpassing existing multimodal approaches. Our proposed framework shows significant improvements in capturing intricate inter-modal relationships and its robustness in medical diagnosis that establishes a framework for future research in multimodal learning in the healthcare sector.

Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful multi-modal models is highly suboptimal for intra-modal tasks like image-to-image retrieval. We argue that this is inherently due to the CLIP-style inter-modal contrastive loss that does not enforce any intra-modal constraints, leading to what we call intra-modal misalignment. To demonstrate this, we leverage two optimization-based modality inversion techniques that map representations from their input modality to the complementary one without any need for auxiliary data or additional trained adapters. We empirically show that, in the intra-modal tasks of image-to-image and text-to-text retrieval, approaching these tasks inter-modally significantly improves performance with respect to intra-modal baselines on more than fifteen datasets. Additionally, we demonstrate that approaching a native inter-modal task (e.g. zero-shot image classification) intra-modally decreases performance, further validating our findings. Finally, we show that incorporating an intra-modal term in the pre-training objective or narrowing the modality gap between the text and image feature embedding spaces helps reduce the intra-modal misalignment. The code is publicly available at: https://github.com/miccunifi/Cross-the-Gap.

Text-to-image person retrieval aims to identify the target person based on a given textual description query. The primary challenge is to learn the mapping of visual and textual modalities into a common latent space. Prior works have attempted to address this challenge by leveraging separately pre-trained unimodal models to extract visual and textual features. However, these approaches lack the necessary underlying alignment capabilities required to match multimodal data effectively. Besides, these works use prior information to explore explicit part alignments, which may lead to the distortion of intra-modality information. To alleviate these issues, we present IRRA: a cross-modal Implicit Relation Reasoning and Aligning framework that learns relations between local visual-textual tokens and enhances global image-text matching without requiring additional prior supervision. Specifically, we first design an Implicit Relation Reasoning module in a masked language modeling paradigm. This achieves cross-modal interaction by integrating the visual cues into the textual tokens with a cross-modal multimodal interaction encoder. Secondly, to globally align the visual and textual embeddings, Similarity Distribution Matching is proposed to minimize the KL divergence between image-text similarity distributions and the normalized label matching distributions. The proposed method achieves new state-of-the-art results on all three public datasets, with a notable margin of about 3%-9% for Rank-1 accuracy compared to prior methods.

Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation between the text and image modalities. Since this strong assumption is often invalid in real-world scenarios, we choose to implicitly model the cross-modal correlation for large-scale multi-modal pre-training, which is the focus of the Chinese project `WenLan' led by our team. Specifically, with the weak correlation assumption over image-text pairs, we propose a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. Unlike OpenAI CLIP that adopts a simple contrastive learning method, we devise a more advanced algorithm by adapting the latest method MoCo into the cross-modal scenario. By building a large queue-based dictionary, our BriVL can incorporate more negative samples in limited GPU resources. We further construct a large Chinese multi-source image-text dataset called RUC-CAS-WenLan for pre-training our BriVL model. Extensive experiments demonstrate that the pre-trained BriVL model outperforms both UNITER and OpenAI CLIP on various downstream tasks.

Cross-modal retrieval methods build a common representation space for samples from multiple modalities, typically from the vision and the language domains. For images and their captions, the multiplicity of the correspondences makes the task particularly challenging. Given an image (respectively a caption), there are multiple captions (respectively images) that equally make sense. In this paper, we argue that deterministic functions are not sufficiently powerful to capture such one-to-many correspondences. Instead, we propose to use Probabilistic Cross-Modal Embedding (PCME), where samples from the different modalities are represented as probabilistic distributions in the common embedding space. Since common benchmarks such as COCO suffer from non-exhaustive annotations for cross-modal matches, we propose to additionally evaluate retrieval on the CUB dataset, a smaller yet clean database where all possible image-caption pairs are annotated. We extensively ablate PCME and demonstrate that it not only improves the retrieval performance over its deterministic counterpart but also provides uncertainty estimates that render the embeddings more interpretable. Code is available at https://github.com/naver-ai/pcme

The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fused purely by attention multiple times to complement each other. Furthermore, to reduce computation, we develop a simple yet effective token fusion module based on cross attention, which uses a single token for each branch as a query to exchange information with other branches. Our proposed cross-attention only requires linear time for both computational and memory complexity instead of quadratic time otherwise. Extensive experiments demonstrate that our approach performs better than or on par with several concurrent works on vision transformer, in addition to efficient CNN models. For example, on the ImageNet1K dataset, with some architectural changes, our approach outperforms the recent DeiT by a large margin of 2\% with a small to moderate increase in FLOPs and model parameters. Our source codes and models are available at https://github.com/IBM/CrossViT.

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than fusion-encoder models and enable the pre-computation of images and text during inference. However, the shallow interaction module used in dual-encoder models is insufficient to handle complex vision-language understanding tasks. In order to learn deep interactions of images and text, we introduce cross-modal attention distillation, which uses the image-to-text and text-to-image attention distributions of a fusion-encoder model to guide the training of our dual-encoder model. In addition, we show that applying the cross-modal attention distillation for both pre-training and fine-tuning stages achieves further improvements. Experimental results demonstrate that the distilled dual-encoder model achieves competitive performance for visual reasoning, visual entailment and visual question answering tasks while enjoying a much faster inference speed than fusion-encoder models. Our code and models will be publicly available at https://github.com/kugwzk/Distilled-DualEncoder.

Image matching for both cross-view and cross-modality plays a critical role in multimodal perception. In practice, the modality gap caused by different imaging systems/styles poses great challenges to the matching task. Existing works try to extract invariant features for specific modalities and train on limited datasets, showing poor generalization. In this paper, we present MINIMA, a unified image matching framework for multiple cross-modal cases. Without pursuing fancy modules, our MINIMA aims to enhance universal performance from the perspective of data scaling up. For such purpose, we propose a simple yet effective data engine that can freely produce a large dataset containing multiple modalities, rich scenarios, and accurate matching labels. Specifically, we scale up the modalities from cheap but rich RGB-only matching data, by means of generative models. Under this setting, the matching labels and rich diversity of the RGB dataset are well inherited by the generated multimodal data. Benefiting from this, we construct MD-syn, a new comprehensive dataset that fills the data gap for general multimodal image matching. With MD-syn, we can directly train any advanced matching pipeline on randomly selected modality pairs to obtain cross-modal ability. Extensive experiments on in-domain and zero-shot matching tasks, including 19 cross-modal cases, demonstrate that our MINIMA can significantly outperform the baselines and even surpass modality-specific methods. The dataset and code are available at https://github.com/LSXI7/MINIMA .

Advancements in language foundation models have primarily fueled the recent surge in artificial intelligence. In contrast, generative learning of non-textual modalities, especially videos, significantly trails behind language modeling. This thesis chronicles our endeavor to build multi-task models for generating videos and other modalities under diverse conditions, as well as for understanding and compression applications. Given the high dimensionality of visual data, we pursue concise and accurate latent representations. Our video-native spatial-temporal tokenizers preserve high fidelity. We unveil a novel approach to mapping bidirectionally between visual observation and interpretable lexical terms. Furthermore, our scalable visual token representation proves beneficial across generation, compression, and understanding tasks. This achievement marks the first instances of language models surpassing diffusion models in visual synthesis and a video tokenizer outperforming industry-standard codecs. Within these multi-modal latent spaces, we study the design of multi-task generative models. Our masked multi-task transformer excels at the quality, efficiency, and flexibility of video generation. We enable a frozen language model, trained solely on text, to generate visual content. Finally, we build a scalable generative multi-modal transformer trained from scratch, enabling the generation of videos containing high-fidelity motion with the corresponding audio given diverse conditions. Throughout the course, we have shown the effectiveness of integrating multiple tasks, crafting high-fidelity latent representation, and generating multiple modalities. This work suggests intriguing potential for future exploration in generating non-textual data and enabling real-time, interactive experiences across various media forms.

This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art approaches in the two subfields of Deep Learning individually. Further, modeling frameworks are discussed where one modality is transformed into the other, as well as models in which one modality is utilized to enhance representation learning for the other. To conclude the second part, architectures with a focus on handling both modalities simultaneously are introduced. Finally, we also cover other modalities as well as general-purpose multi-modal models, which are able to handle different tasks on different modalities within one unified architecture. One interesting application (Generative Art) eventually caps off this booklet.

Building artificial intelligence (AI) systems on top of a set of foundation models (FMs) is becoming a new paradigm in AI research. Their representative and generative abilities learnt from vast amounts of data can be easily adapted and transferred to a wide range of downstream tasks without extra training from scratch. However, leveraging FMs in cross-modal generation remains under-researched when audio modality is involved. On the other hand, automatically generating semantically-relevant sound from visual input is an important problem in cross-modal generation studies. To solve this vision-to-audio (V2A) generation problem, existing methods tend to design and build complex systems from scratch using modestly sized datasets. In this paper, we propose a lightweight solution to this problem by leveraging foundation models, specifically CLIP, CLAP, and AudioLDM. We first investigate the domain gap between the latent space of the visual CLIP and the auditory CLAP models. Then we propose a simple yet effective mapper mechanism (V2A-Mapper) to bridge the domain gap by translating the visual input between CLIP and CLAP spaces. Conditioned on the translated CLAP embedding, pretrained audio generative FM AudioLDM is adopted to produce high-fidelity and visually-aligned sound. Compared to previous approaches, our method only requires a quick training of the V2A-Mapper. We further analyze and conduct extensive experiments on the choice of the V2A-Mapper and show that a generative mapper is better at fidelity and variability (FD) while a regression mapper is slightly better at relevance (CS). Both objective and subjective evaluation on two V2A datasets demonstrate the superiority of our proposed method compared to current state-of-the-art approaches - trained with 86% fewer parameters but achieving 53% and 19% improvement in FD and CS, respectively.

The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detection and panoptic segmentation). Originated from Natural Language Processing (NLP), transformer architectures, consisting of self-attention and cross-attention, effectively learn long-range interactions between elements in a sequence. However, we observe that most existing transformer-based vision models simply borrow the idea from NLP, neglecting the crucial difference between languages and images, particularly the extremely large sequence length of spatially flattened pixel features. This subsequently impedes the learning in cross-attention between pixel features and object queries. In this paper, we rethink the relationship between pixels and object queries and propose to reformulate the cross-attention learning as a clustering process. Inspired by the traditional k-means clustering algorithm, we develop a k-means Mask Xformer (kMaX-DeepLab) for segmentation tasks, which not only improves the state-of-the-art, but also enjoys a simple and elegant design. As a result, our kMaX-DeepLab achieves a new state-of-the-art performance on COCO val set with 58.0% PQ, Cityscapes val set with 68.4% PQ, 44.0% AP, and 83.5% mIoU, and ADE20K val set with 50.9% PQ and 55.2% mIoU without test-time augmentation or external dataset. We hope our work can shed some light on designing transformers tailored for vision tasks. TensorFlow code and models are available at https://github.com/google-research/deeplab2 A PyTorch re-implementation is also available at https://github.com/bytedance/kmax-deeplab

Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., ViT) are following the same trend, achieving the best performance on challenging benchmarks. With the abundance of such unimodal models, a natural question arises; do we need also to follow this trend to tackle multimodal tasks? In this work, we propose to rather direct effort to efficient adaptations of existing models, and propose to augment Language Models with perception. Existing approaches for adapting pretrained models for vision-language tasks still rely on several key components that hinder their efficiency. In particular, they still train a large number of parameters, rely on large multimodal pretraining, use encoders (e.g., CLIP) trained on huge image-text datasets, and add significant inference overhead. In addition, most of these approaches have focused on Zero-Shot and In Context Learning, with little to no effort on direct finetuning. We investigate the minimal computational effort needed to adapt unimodal models for multimodal tasks and propose a new challenging setup, alongside different approaches, that efficiently adapts unimodal pretrained models. We show that by freezing more than 99\% of total parameters, training only one linear projection layer, and prepending only one trainable token, our approach (dubbed eP-ALM) significantly outperforms other baselines on VQA and Captioning across Image, Video, and Audio modalities, following the proposed setup. The code will be available here: https://github.com/mshukor/eP-ALM.

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering the model incapable of focusing only on relevant complementary information for fusion. To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. Specifically, we propose an architecture consisting of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using our proposed self-supervised model adaptation fusion mechanism which optimally combines complementary features. As intermediate representations are not aligned across modalities, we introduce an attention scheme for better correlation. In addition, we propose a computationally efficient unimodal segmentation architecture termed AdapNet++ that incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling that has a larger effective receptive field with more than 10x fewer parameters, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on several benchmarks demonstrate that both our unimodal and multimodal architectures achieve state-of-the-art performance.

Vision-language pre-training and instruction tuning have demonstrated general-purpose capabilities in 2D visual reasoning tasks by aligning visual encoders with state-of-the-art large language models (LLMs). In this paper, we introduce a simple, yet effective, cross-modality framework built atop frozen LLMs that allows the integration of various modalities without extensive modality-specific customization. To facilitate instruction-modality fine-tuning, we collect high-quality instruction tuning data in an automatic and scalable manner, composed of 24K QA samples for audio and 250K QA samples for 3D. Leveraging instruction-aware representations, our model performs comparably with leading-edge counterparts without the need of extensive modality-specific pre-training or customization. Furthermore, our approach demonstrates cross-modal reasoning abilities across two or more input modalities, despite each modality projection being trained individually. To study the model's cross-modal abilities, we contribute a novel Discriminative Cross-modal Reasoning (DisCRn) evaluation task, comprising 9K audio-video QA samples and 28K image-3D QA samples that require the model to reason discriminatively across disparate input modalities.

Building cross-modal applications is challenging due to limited paired multi-modal data. Recent works have shown that leveraging a pre-trained multi-modal contrastive representation space enables cross-modal tasks to be learned from uni-modal data. This is based on the assumption that contrastive optimization makes embeddings from different modalities interchangeable. However, this assumption is under-explored due to the poorly understood geometry of the multi-modal contrastive space, where a modality gap exists. In our study, we provide a theoretical explanation of this space's geometry and introduce a three-step method, C^3 (Connect, Collapse, Corrupt), to bridge the modality gap, enhancing the interchangeability of embeddings. Our C^3 method significantly improves cross-modal learning from uni-modal data, achieving state-of-the-art results on zero-shot image / audio / video captioning and text-to-image generation.

Semantic scene completion (SSC) requires an accurate understanding of the geometric and semantic relationships between the objects in the 3D scene for reasoning the occluded objects. The popular SSC methods voxelize the 3D objects, allowing the deep 3D convolutional network (3D CNN) to learn the object relationships from the complex scenes. However, the current networks lack the controllable kernels to model the object relationship across multiple views, where appropriate views provide the relevant information for suggesting the existence of the occluded objects. In this paper, we propose Cross-View Synthesis Transformer (CVSformer), which consists of Multi-View Feature Synthesis and Cross-View Transformer for learning cross-view object relationships. In the multi-view feature synthesis, we use a set of 3D convolutional kernels rotated differently to compute the multi-view features for each voxel. In the cross-view transformer, we employ the cross-view fusion to comprehensively learn the cross-view relationships, which form useful information for enhancing the features of individual views. We use the enhanced features to predict the geometric occupancies and semantic labels of all voxels. We evaluate CVSformer on public datasets, where CVSformer yields state-of-the-art results.

Enabling effective brain-computer interfaces requires understanding how the human brain encodes stimuli across modalities such as visual, language (or text), etc. Brain encoding aims at constructing fMRI brain activity given a stimulus. There exists a plethora of neural encoding models which study brain encoding for single mode stimuli: visual (pretrained CNNs) or text (pretrained language models). Few recent papers have also obtained separate visual and text representation models and performed late-fusion using simple heuristics. However, previous work has failed to explore: (a) the effectiveness of image Transformer models for encoding visual stimuli, and (b) co-attentive multi-modal modeling for visual and text reasoning. In this paper, we systematically explore the efficacy of image Transformers (ViT, DEiT, and BEiT) and multi-modal Transformers (VisualBERT, LXMERT, and CLIP) for brain encoding. Extensive experiments on two popular datasets, BOLD5000 and Pereira, provide the following insights. (1) To the best of our knowledge, we are the first to investigate the effectiveness of image and multi-modal Transformers for brain encoding. (2) We find that VisualBERT, a multi-modal Transformer, significantly outperforms previously proposed single-mode CNNs, image Transformers as well as other previously proposed multi-modal models, thereby establishing new state-of-the-art. The supremacy of visio-linguistic models raises the question of whether the responses elicited in the visual regions are affected implicitly by linguistic processing even when passively viewing images. Future fMRI tasks can verify this computational insight in an appropriate experimental setting.

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific paradigm, leading to inefficient collaboration between tasks and high marginal costs of developing perception models for new tasks. In this paper, we present a generic perception architecture named Uni-Perceiver, which processes a variety of modalities and tasks with unified modeling and shared parameters. Specifically, Uni-Perceiver encodes different task inputs and targets from arbitrary modalities into a unified representation space with a modality-agnostic Transformer encoder and lightweight modality-specific tokenizers. Different perception tasks are modeled as the same formulation, that is, finding the maximum likelihood target for each input through the similarity of their representations. The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks. The performance can be improved to a level close to state-of-the-art methods by conducting prompt tuning on 1% of downstream task data. Full-data fine-tuning further delivers results on par with or better than state-of-the-art results. Code shall be released.

We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB image (hence "multi-modal"), and II) its training objective accordingly includes predicting multiple outputs besides the RGB image (hence "multi-task"). We make use of masking (across image patches and input modalities) to make training MultiMAE tractable as well as to ensure cross-modality predictive coding is indeed learned by the network. We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks. In particular, the same exact pre-trained network can be flexibly used when additional information besides RGB images is available or when no information other than RGB is available - in all configurations yielding competitive to or significantly better results than the baselines. To avoid needing training datasets with multiple modalities and tasks, we train MultiMAE entirely using pseudo labeling, which makes the framework widely applicable to any RGB dataset. The experiments are performed on multiple transfer tasks (image classification, semantic segmentation, depth estimation) and datasets (ImageNet, ADE20K, Taskonomy, Hypersim, NYUv2). The results show an intriguingly impressive capability by the model in cross-modal/task predictive coding and transfer.

Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill complementary knowledge from Transformer to convolutional neural network (CNN). However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN. They may not be suitable when applying to cross-architecture scenarios, such as from Transformer to CNN. To deal with this problem, a novel cross-architecture knowledge distillation method is proposed. Specifically, instead of directly mimicking output/intermediate features of the teacher, partially cross attention projector and group-wise linear projector are introduced to align the student features with the teacher's in two projected feature spaces. And a multi-view robust training scheme is further presented to improve the robustness and stability of the framework. Extensive experiments show that the proposed method outperforms 14 state-of-the-arts on both small-scale and large-scale datasets.

Existing multimodal conditional image synthesis (MCIS) methods generate images conditioned on any combinations of various modalities that require all of them must be exactly conformed, hindering the synthesis controllability and leaving the potential of cross-modality under-exploited. To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i.e., composed multimodal conditional image synthesis (CMCIS). Specifically, we observe two challenging issues of the proposed CMCIS task, i.e., the modality coordination problem and the modality imbalance problem. To tackle these issues, we introduce a Mixture-of-Modality-Tokens Transformer (MMoT) that adaptively fuses fine-grained multimodal control signals, a multimodal balanced training loss to stabilize the optimization of each modality, and a multimodal sampling guidance to balance the strength of each modality control signal. Comprehensive experimental results demonstrate that MMoT achieves superior performance on both unimodal conditional image synthesis (UCIS) and MCIS tasks with high-quality and faithful image synthesis on complex multimodal conditions. The project website is available at https://jabir-zheng.github.io/MMoT.

In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agnostic pretraining tasks, cross-modal aligning contrast and intra-modal denoising contrast, which align the semantic space of different modalities and capture fine-grained details within modalities concurrently. With the scaling-friendly architecture and pretraining tasks, ONE-PEACE has the potential to expand to unlimited modalities. Without using any vision or language pretrained model for initialization, ONE-PEACE achieves leading results on a wide range of uni-modal and multi-modal tasks, including image classification (ImageNet), semantic segmentation (ADE20K), audio-text retrieval (AudioCaps, Clotho), audio classification (ESC-50, FSD50K, VGGSound), audio question answering (AVQA), image-text retrieval (MSCOCO, Flickr30K), and visual grounding (RefCOCO/+/g). Code is available at https://github.com/OFA-Sys/ONE-PEACE.

Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders embedding performance. Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck. In this work, we identify three criteria for high-quality synthetic multimodal data. First, broad scope ensures that the generated data covers diverse tasks and modalities, making it applicable to various downstream scenarios. Second, robust cross-modal alignment makes different modalities semantically consistent. Third, high fidelity ensures that the synthetic data maintains realistic details to enhance its reliability. Guided by these principles, we synthesize datasets that: (1) cover a wide range of tasks, modality combinations, and languages, (2) are generated via a deep thinking process within a single pass of a multimodal large language model, and (3) incorporate real-world images with accurate and relevant texts, ensuring fidelity through self-evaluation and refinement. Leveraging these high-quality synthetic and labeled datasets, we train a multimodal multilingual E5 model mmE5. Extensive experiments demonstrate that mmE5 achieves state-of-the-art performance on the MMEB Benchmark and superior multilingual performance on the XTD benchmark. Our codes, datasets and models are released in https://github.com/haon-chen/mmE5.

In this paper, we tackle two challenges in multimodal learning for visual recognition: 1) when missing-modality occurs either during training or testing in real-world situations; and 2) when the computation resources are not available to finetune on heavy transformer models. To this end, we propose to utilize prompt learning and mitigate the above two challenges together. Specifically, our modality-missing-aware prompts can be plugged into multimodal transformers to handle general missing-modality cases, while only requiring less than 1% learnable parameters compared to training the entire model. We further explore the effect of different prompt configurations and analyze the robustness to missing modality. Extensive experiments are conducted to show the effectiveness of our prompt learning framework that improves the performance under various missing-modality cases, while alleviating the requirement of heavy model re-training. Code is available.

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has mainly focused on investigating white-box attacks. In this paper, we present the first study to investigate the adversarial transferability of recent VLP models. We observe that existing methods exhibit much lower transferability, compared to the strong attack performance in white-box settings. The transferability degradation is partly caused by the under-utilization of cross-modal interactions. Particularly, unlike unimodal learning, VLP models rely heavily on cross-modal interactions and the multimodal alignments are many-to-many, e.g., an image can be described in various natural languages. To this end, we propose a highly transferable Set-level Guidance Attack (SGA) that thoroughly leverages modality interactions and incorporates alignment-preserving augmentation with cross-modal guidance. Experimental results demonstrate that SGA could generate adversarial examples that can strongly transfer across different VLP models on multiple downstream vision-language tasks. On image-text retrieval, SGA significantly enhances the attack success rate for transfer attacks from ALBEF to TCL by a large margin (at least 9.78% and up to 30.21%), compared to the state-of-the-art.

Modern retrieval systems often struggle with upgrading to new and more powerful models due to the incompatibility of embeddings between the old and new models. This necessitates a costly process known as backfilling, which involves re-computing the embeddings for a large number of data samples. In vision, Backward-compatible Training (BT) has been proposed to ensure that the new model aligns with the old model's embeddings. This paper extends the concept of vision-only BT to the field of cross-modal retrieval, marking the first attempt to address Cross-modal BT (XBT). Our goal is to achieve backward-compatibility between Vision-Language Pretraining (VLP) models, such as CLIP, for the cross-modal retrieval task. To address XBT challenges, we propose an efficient solution: a projection module that maps the new model's embeddings to those of the old model. This module, pretrained solely with text data, significantly reduces the number of image-text pairs required for XBT learning, and, once it is pretrained, it avoids using the old model during training. Furthermore, we utilize parameter-efficient training strategies that improve efficiency and preserve the off-the-shelf new model's knowledge by avoiding any modifications. Experimental results on cross-modal retrieval datasets demonstrate the effectiveness of XBT and its potential to enable backfill-free upgrades when a new VLP model emerges.

Prior work has studied different visual modalities in isolation and developed separate architectures for recognition of images, videos, and 3D data. Instead, in this paper, we propose a single model which excels at classifying images, videos, and single-view 3D data using exactly the same model parameters. Our 'Omnivore' model leverages the flexibility of transformer-based architectures and is trained jointly on classification tasks from different modalities. Omnivore is simple to train, uses off-the-shelf standard datasets, and performs at-par or better than modality-specific models of the same size. A single Omnivore model obtains 86.0% on ImageNet, 84.1% on Kinetics, and 67.1% on SUN RGB-D. After finetuning, our models outperform prior work on a variety of vision tasks and generalize across modalities. Omnivore's shared visual representation naturally enables cross-modal recognition without access to correspondences between modalities. We hope our results motivate researchers to model visual modalities together.

Deception detection in conversations is a challenging yet important task, having pivotal applications in many fields such as credibility assessment in business, multimedia anti-frauds, and custom security. Despite this, deception detection research is hindered by the lack of high-quality deception datasets, as well as the difficulties of learning multimodal features effectively. To address this issue, we introduce DOLOSThe name ``DOLOS" comes from Greek mythology., the largest gameshow deception detection dataset with rich deceptive conversations. DOLOS includes 1,675 video clips featuring 213 subjects, and it has been labeled with audio-visual feature annotations. We provide train-test, duration, and gender protocols to investigate the impact of different factors. We benchmark our dataset on previously proposed deception detection approaches. To further improve the performance by fine-tuning fewer parameters, we propose Parameter-Efficient Crossmodal Learning (PECL), where a Uniform Temporal Adapter (UT-Adapter) explores temporal attention in transformer-based architectures, and a crossmodal fusion module, Plug-in Audio-Visual Fusion (PAVF), combines crossmodal information from audio-visual features. Based on the rich fine-grained audio-visual annotations on DOLOS, we also exploit multi-task learning to enhance performance by concurrently predicting deception and audio-visual features. Experimental results demonstrate the desired quality of the DOLOS dataset and the effectiveness of the PECL. The DOLOS dataset and the source codes are available at https://github.com/NMS05/Audio-Visual-Deception-Detection-DOLOS-Dataset-and-Parameter-Efficient-Crossmodal-Learning/tree/main.

Large-kernel convolutional neural networks (ConvNets) have recently received extensive research attention, but there are two unresolved and critical issues that demand further investigation. 1) The architectures of existing large-kernel ConvNets largely follow the design principles of conventional ConvNets or transformers, while the architectural design for large-kernel ConvNets remains under-addressed. 2) As transformers have dominated multiple modalities, it remains to be investigated whether ConvNets also have a strong universal perception ability in domains beyond vision. In this paper, we contribute from two aspects. 1) We propose four architectural guidelines for designing large-kernel ConvNets, the core of which is to exploit the essential characteristics of large kernels that distinguish them from small kernels - they can see wide without going deep. Following such guidelines, our proposed large-kernel ConvNet shows leading performance in image recognition. For example, our models achieve an ImageNet accuracy of 88.0%, ADE20K mIoU of 55.6%, and COCO box AP of 56.4%, demonstrating better performance and higher speed than a number of recently proposed powerful competitors. 2) We discover that large kernels are the key to unlocking the exceptional performance of ConvNets in domains where they were originally not proficient. With certain modality-related preprocessing approaches, the proposed model achieves state-of-the-art performance on time-series forecasting and audio recognition tasks even without modality-specific customization to the architecture. Code and all the models at https://github.com/AILab-CVC/UniRepLKNet.

Due to the remarkable capabilities of powerful Large Language Models (LLMs) in effectively following instructions, there has been a growing number of assistants in the community to assist humans. Recently, significant progress has been made in the development of Vision Language Models (VLMs), expanding the capabilities of LLMs and enabling them to execute more diverse instructions. However, it is foreseeable that models will likely need to handle tasks involving additional modalities such as speech, video, and others. This poses a particularly prominent challenge of dealing with the complexity of mixed modalities. To address this, we introduce a novel architecture called PILL: Plug Into LLM with adapter expert and attention gate to better decouple these complex modalities and leverage efficient fine-tuning. We introduce two modules: Firstly, utilizing Mixture-of-Modality-Adapter-Expert to independently handle different modalities, enabling better adaptation to downstream tasks while preserving the expressive capability of the original model. Secondly, by introducing Modality-Attention-Gating, which enables adaptive control of the contribution of modality tokens to the overall representation. In addition, we have made improvements to the Adapter to enhance its learning and expressive capabilities. Experimental results demonstrate that our approach exhibits competitive performance compared to other mainstream methods for modality fusion. For researchers interested in our work, we provide free access to the code and models at https://github.com/DsaltYfish/PILL.

Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the diversity and heterogeneity of tasks and modalities. A promising solution is unification, allowing the support of a myriad of tasks and modalities within one unified framework. While few large models (e.g., Flamingo (Alayrac et al., 2022), trained on massive datasets, can support more than two modalities, current small to mid-scale unified models are still limited to 2 modalities, usually image-text or video-text. The question that we ask is: is it possible to build efficiently a unified model that can support all modalities? To answer this, we propose UnIVAL, a step further towards this ambitious goal. Without relying on fancy datasets sizes or models with billions of parameters, the ~ 0.25B parameter UnIVAL model goes beyond two modalities and unifies text, images, video, and audio into a single model. Our model is efficiently pretrained on many tasks, based on task balancing and multimodal curriculum learning. UnIVAL shows competitive performance to existing state-of-the-art approaches, across image and video-text tasks. The feature representations learned from image and video-text modalities, allows the model to achieve competitive performance when finetuned on audio-text tasks, despite not being pretrained on audio. Thanks to the unified model, we propose a novel study on multimodal model merging via weight interpolation of models trained on different multimodal tasks, showing their benefits in particular for out-of-distribution generalization. Finally, we motivate unification by showing the synergy between tasks. The model weights and code are released here: https://github.com/mshukor/UnIVAL.

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural language processing models, we propose a unified-modal SpeechT5 framework that explores the encoder-decoder pre-training for self-supervised speech/text representation learning. The SpeechT5 framework consists of a shared encoder-decoder network and six modal-specific (speech/text) pre/post-nets. After preprocessing the input speech/text through the pre-nets, the shared encoder-decoder network models the sequence-to-sequence transformation, and then the post-nets generate the output in the speech/text modality based on the output of the decoder. Leveraging large-scale unlabeled speech and text data, we pre-train SpeechT5 to learn a unified-modal representation, hoping to improve the modeling capability for both speech and text. To align the textual and speech information into this unified semantic space, we propose a cross-modal vector quantization approach that randomly mixes up speech/text states with latent units as the interface between encoder and decoder. Extensive evaluations show the superiority of the proposed SpeechT5 framework on a wide variety of spoken language processing tasks, including automatic speech recognition, speech synthesis, speech translation, voice conversion, speech enhancement, and speaker identification. We release our code and model at https://github.com/microsoft/SpeechT5.

We present PhiloBERTA, a cross-lingual transformer model that measures semantic relationships between ancient Greek and Latin lexicons. Through analysis of selected term pairs from classical texts, we use contextual embeddings and angular similarity metrics to identify precise semantic alignments. Our results show that etymologically related pairs demonstrate significantly higher similarity scores, particularly for abstract philosophical concepts such as epist\=em\=e (scientia) and dikaiosyn\=e (iustitia). Statistical analysis reveals consistent patterns in these relationships (p = 0.012), with etymologically related pairs showing remarkably stable semantic preservation compared to control pairs. These findings establish a quantitative framework for examining how philosophical concepts moved between Greek and Latin traditions, offering new methods for classical philological research.

In the field of multi-modal language models, the majority of methods are built on an architecture similar to LLaVA. These models use a single-layer ViT feature as a visual prompt, directly feeding it into the language models alongside textual tokens. However, when dealing with long sequences of visual signals or inputs such as videos, the self-attention mechanism of language models can lead to significant computational overhead. Additionally, using single-layer ViT features makes it challenging for large language models to perceive visual signals fully. This paper proposes an efficient multi-modal language model to minimize computational costs while enabling the model to perceive visual signals as comprehensively as possible. Our method primarily includes: (1) employing cross-attention to image-text interaction similar to Flamingo. (2) utilize hierarchical ViT features. (3) introduce the Mixture of Experts (MoE) mechanism to enhance model effectiveness. Our model achieves competitive scores on public multi-modal benchmarks and performs well in tasks such as image captioning and video captioning.

Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual information, remains a significant challenge. Existing visual-language models often struggle to effectively analyze and reason visual content, resulting in suboptimal performance on complex reasoning tasks. Moreover, the absence of comprehensive benchmarks hinders the accurate assessment of multimodal reasoning capabilities. In this paper, we introduce R1-Onevision, a multimodal reasoning model designed to bridge the gap between visual perception and deep reasoning. To achieve this, we propose a cross-modal reasoning pipeline that transforms images into formal textural representations, enabling precise language-based reasoning. Leveraging this pipeline, we construct the R1-Onevision dataset which provides detailed, step-by-step multimodal reasoning annotations across diverse domains. We further develop the R1-Onevision model through supervised fine-tuning and reinforcement learning to cultivate advanced reasoning and robust generalization abilities. To comprehensively evaluate multimodal reasoning performance across different grades, we introduce R1-Onevision-Bench, a benchmark aligned with human educational stages, covering exams from junior high school to university and beyond. Experimental results show that R1-Onevision achieves state-of-the-art performance, outperforming models such as GPT-4o and Qwen2.5-VL on multiple challenging multimodal reasoning benchmarks.

State Space Models (SSMs) have emerged as efficient alternatives to Transformers for sequential modeling, but their inability to leverage modality-specific features limits their performance in multi-modal pretraining. Here, we propose Mixture-of-Mamba, a novel SSM architecture that introduces modality-aware sparsity through modality-specific parameterization of the Mamba block. Building on Mixture-of-Transformers (W. Liang et al. arXiv:2411.04996; 2024), we extend the benefits of modality-aware sparsity to SSMs while preserving their computational efficiency. We evaluate Mixture-of-Mamba across three multi-modal pretraining settings: Transfusion (interleaved text and continuous image tokens with diffusion loss), Chameleon (interleaved text and discrete image tokens), and an extended three-modality framework incorporating speech. Mixture-of-Mamba consistently reaches the same loss values at earlier training steps with significantly reduced computational costs. In the Transfusion setting, Mixture-of-Mamba achieves equivalent image loss using only 34.76% of the training FLOPs at the 1.4B scale. In the Chameleon setting, Mixture-of-Mamba reaches similar image loss with just 42.50% of the FLOPs at the 1.4B scale, and similar text loss with just 65.40% of the FLOPs. In the three-modality setting, MoM matches speech loss at 24.80% of the FLOPs at the 1.4B scale. Our ablation study highlights the synergistic effects of decoupling projection components, where joint decoupling yields greater gains than individual modifications. These results establish modality-aware sparsity as a versatile and effective design principle, extending its impact from Transformers to SSMs and setting new benchmarks in multi-modal pretraining. Our code can be accessed at https://github.com/Weixin-Liang/Mixture-of-Mamba

Over the eight months since its release, ChatGPT and its underlying model, GPT3.5, have garnered massive attention, due to their potent mix of capability and accessibility. While a niche-industry of papers have emerged examining the scope of capabilities these models possess, the information fed to and extracted from these networks has been either natural language text or stylized, code-like language. Drawing inspiration from the prowess we expect a truly human-level intelligent agent to have across multiple signal modalities, in this work we examine GPT3.5's aptitude for visual tasks, where the inputs feature content provided as ASCII-art without overt distillation into a lingual summary. We conduct experiments analyzing the model's performance on image recognition tasks after various transforms typical in visual settings, trials investigating knowledge of image parts, and tasks covering image generation.

We present Integrated Multimodal Perception (IMP), a simple and scalable multimodal multi-task training and modeling approach. IMP integrates multimodal inputs including image, video, text, and audio into a single Transformer encoder with minimal modality-specific components. IMP makes use of a novel design that combines Alternating Gradient Descent (AGD) and Mixture-of-Experts (MoE) for efficient model \& task scaling. We conduct extensive empirical studies about IMP and reveal the following key insights: 1) performing gradient descent updates by alternating on diverse heterogeneous modalities, loss functions, and tasks, while also varying input resolutions, efficiently improves multimodal understanding. 2) model sparsification with MoE on a single modality-agnostic encoder substantially improves the performance, outperforming dense models that use modality-specific encoders or additional fusion layers and greatly mitigating the conflicts between modalities. IMP achieves competitive performance on a wide range of downstream tasks including image classification, video classification, image-text, and video-text retrieval. Most notably, we train a sparse IMP-MoE-L focusing on video tasks that achieves new state-of-the-art in zero-shot video classification. Our model achieves 77.0% on Kinetics-400, 76.8% on Kinetics-600, and 76.8% on Kinetics-700 zero-shot classification accuracy, improving the previous state-of-the-art by +5%, +6.7%, and +5.8%, respectively, while using only 15% of their total training computational cost.

Modern machine learning systems rely on large datasets to attain broad generalization, and this often poses a challenge in robot learning, where each robotic platform and task might have only a small dataset. By training a single policy across many different kinds of robots, a robot learning method can leverage much broader and more diverse datasets, which in turn can lead to better generalization and robustness. However, training a single policy on multi-robot data is challenging because robots can have widely varying sensors, actuators, and control frequencies. We propose CrossFormer, a scalable and flexible transformer-based policy that can consume data from any embodiment. We train CrossFormer on the largest and most diverse dataset to date, 900K trajectories across 20 different robot embodiments. We demonstrate that the same network weights can control vastly different robots, including single and dual arm manipulation systems, wheeled robots, quadcopters, and quadrupeds. Unlike prior work, our model does not require manual alignment of the observation or action spaces. Extensive experiments in the real world show that our method matches the performance of specialist policies tailored for each embodiment, while also significantly outperforming the prior state of the art in cross-embodiment learning.

Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.

The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present a unified multimodal generation model that can conduct both the "modality translation" and "multi-modality generation" tasks using a single model, performing text-based, image-based, and even vision-language simultaneous generation. Specifically, we unify the discrete diffusion process for multimodal signals by proposing a unified transition matrix. Moreover, we design a mutual attention module with fused embedding layer and a unified objective function to emphasise the inter-modal linkages, which are vital for multi-modality generation. Extensive experiments indicate that our proposed method can perform comparably to the state-of-the-art solutions in various generation tasks.

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different implementations for better performance, e.g., Post-LayerNorm for BERT, and Pre-LayerNorm for GPT and vision Transformers. We call for the development of Foundation Transformer for true general-purpose modeling, which serves as a go-to architecture for various tasks and modalities with guaranteed training stability. In this work, we introduce a Transformer variant, named Magneto, to fulfill the goal. Specifically, we propose Sub-LayerNorm for good expressivity, and the initialization strategy theoretically derived from DeepNet for stable scaling up. Extensive experiments demonstrate its superior performance and better stability than the de facto Transformer variants designed for various applications, including language modeling (i.e., BERT, and GPT), machine translation, vision pretraining (i.e., BEiT), speech recognition, and multimodal pretraining (i.e., BEiT-3).

We present ImageBind, an approach to learn a joint embedding across six different modalities - images, text, audio, depth, thermal, and IMU data. We show that all combinations of paired data are not necessary to train such a joint embedding, and only image-paired data is sufficient to bind the modalities together. ImageBind can leverage recent large scale vision-language models, and extends their zero-shot capabilities to new modalities just by using their natural pairing with images. It enables novel emergent applications 'out-of-the-box' including cross-modal retrieval, composing modalities with arithmetic, cross-modal detection and generation. The emergent capabilities improve with the strength of the image encoder and we set a new state-of-the-art on emergent zero-shot recognition tasks across modalities, outperforming specialist supervised models. Finally, we show strong few-shot recognition results outperforming prior work, and that ImageBind serves as a new way to evaluate vision models for visual and non-visual tasks.

Cross-modal retrieval (CMR) has been extensively applied in various domains, such as multimedia search engines and recommendation systems. Most existing CMR methods focus on image-to-text retrieval, whereas audio-to-text retrieval, a less explored domain, has posed a great challenge due to the difficulty to uncover discriminative features from audio clips and texts. Existing studies are restricted in the following two ways: 1) Most researchers utilize contrastive learning to construct a common subspace where similarities among data can be measured. However, they considers only cross-modal transformation, neglecting the intra-modal separability. Besides, the temperature parameter is not adaptively adjusted along with semantic guidance, which degrades the performance. 2) These methods do not take latent representation reconstruction into account, which is essential for semantic alignment. This paper introduces a novel audio-text oriented CMR approach, termed Contrastive Latent Space Reconstruction Learning (CLSR). CLSR improves contrastive representation learning by taking intra-modal separability into account and adopting an adaptive temperature control strategy. Moreover, the latent representation reconstruction modules are embedded into the CMR framework, which improves modal interaction. Experiments in comparison with some state-of-the-art methods on two audio-text datasets have validated the superiority of CLSR.

Current multimodal and multitask foundation models like 4M or UnifiedIO show promising results, but in practice their out-of-the-box abilities to accept diverse inputs and perform diverse tasks are limited by the (usually rather small) number of modalities and tasks they are trained on. In this paper, we expand upon the capabilities of them by training a single model on tens of highly diverse modalities and by performing co-training on large-scale multimodal datasets and text corpora. This includes training on several semantic and geometric modalities, feature maps from recent state of the art models like DINOv2 and ImageBind, pseudo labels of specialist models like SAM and 4DHumans, and a range of new modalities that allow for novel ways to interact with the model and steer the generation, for example image metadata or color palettes. A crucial step in this process is performing discrete tokenization on various modalities, whether they are image-like, neural network feature maps, vectors, structured data like instance segmentation or human poses, or data that can be represented as text. Through this, we expand on the out-of-the-box capabilities of multimodal models and specifically show the possibility of training one model to solve at least 3x more tasks/modalities than existing ones and doing so without a loss in performance. This enables more fine-grained and controllable multimodal generation capabilities and allows us to study the distillation of models trained on diverse data and objectives into a unified model. We successfully scale the training to a three billion parameter model using tens of modalities and different datasets. The resulting models and training code are open sourced at 4m.epfl.ch.

State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic pretraining for obtaining good performance on a variety of downstream tasks. Generally, such models are often either cross-modal (contrastive) or multi-modal (with earlier fusion) but not both; and they often only target specific modalities or tasks. A promising direction would be to use a single holistic universal model, as a "foundation", that targets all modalities at once -- a true vision and language foundation model should be good at vision tasks, language tasks, and cross- and multi-modal vision and language tasks. We introduce FLAVA as such a model and demonstrate impressive performance on a wide range of 35 tasks spanning these target modalities.

Contrastive language-image pre-training (CLIP) has demonstrated remarkable zero-shot classification ability, namely image classification using novel text labels. Existing works have attempted to enhance CLIP by fine-tuning on downstream tasks, but these have inadvertently led to performance degradation on unseen classes, thus harming zero-shot generalization. This paper aims to address this challenge by leveraging readily available image-text pairs from an external dataset for cross-modal guidance during inference. To this end, we propose X-MoRe, a novel inference method comprising two key steps: (1) cross-modal retrieval and (2) modal-confidence-based ensemble. Given a query image, we harness the power of CLIP's cross-modal representations to retrieve relevant textual information from an external image-text pair dataset. Then, we assign higher weights to the more reliable modality between the original query image and retrieved text, contributing to the final prediction. X-MoRe demonstrates robust performance across a diverse set of tasks without the need for additional training, showcasing the effectiveness of utilizing cross-modal features to maximize CLIP's zero-shot ability.

User interface modeling is inherently multimodal, which involves several distinct types of data: images, structures and language. The tasks are also diverse, including object detection, language generation and grounding. In this paper, we present VUT, a Versatile UI Transformer that takes multimodal input and simultaneously accomplishes 5 distinct tasks with the same model. Our model consists of a multimodal Transformer encoder that jointly encodes UI images and structures, and performs UI object detection when the UI structures are absent in the input. Our model also consists of an auto-regressive Transformer model that encodes the language input and decodes output, for both question-answering and command grounding with respect to the UI. Our experiments show that for most of the tasks, when trained jointly for multi-tasks, VUT substantially reduces the number of models and footprints needed for performing multiple tasks, while achieving accuracy exceeding or on par with baseline models trained for each individual task.

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g., interleaved image, text and video) through a one-model-for-all autoregressive training process. First, visual signals are encoded into embeddings, and together with text tokens form an interleaved input sequence. Emu is then end-to-end trained with a unified objective of classifying the next text token or regressing the next visual embedding in the multimodal sequence. This versatile multimodality empowers the exploration of diverse pretraining data sources at scale, such as videos with interleaved frames and text, webpages with interleaved images and text, as well as web-scale image-text pairs and video-text pairs. Emu can serve as a generalist multimodal interface for both image-to-text and text-to-image tasks, and supports in-context image and text generation. Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models. Extended capabilities such as multimodal assistants via instruction tuning are also demonstrated with impressive performance.

Parameter Efficient Tuning (PET) has gained attention for reducing the number of parameters while maintaining performance and providing better hardware resource savings, but few studies investigate dense prediction tasks and interaction between modalities. In this paper, we do an investigation of efficient tuning problems on referring image segmentation. We propose a novel adapter called Bridger to facilitate cross-modal information exchange and inject task-specific information into the pre-trained model. We also design a lightweight decoder for image segmentation. Our approach achieves comparable or superior performance with only 1.61\% to 3.38\% backbone parameter updates, evaluated on challenging benchmarks. The code is available at https://github.com/kkakkkka/ETRIS.

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the vision-language alignment of pre-trained models in return for improved performance on specific tasks and classes, leading to poorer generalization. In this paper, we first demonstrate that prompt tuning along only one single branch of CLIP (e.g., language or vision) is the reason why the misalignment occurs. Without proper regularization across the learnable parameters in different modalities, prompt learning violates the original pre-training constraints inherent in the two-tower architecture. To address such misalignment, we first propose feature shift, which is defined as the variation of embeddings after introducing the learned prompts, to serve as an explanatory tool. We dive into its relation with generalizability and thereafter propose RESTORE, a multi-modal prompt learning method that exerts explicit constraints on cross-modal consistency. To be more specific, to prevent feature misalignment, a feature shift consistency is introduced to synchronize inter-modal feature shifts by measuring and regularizing the magnitude of discrepancy during prompt tuning. In addition, we propose a "surgery" block to avoid short-cut hacking, where cross-modal misalignment can still be severe if the feature shift of each modality varies drastically at the same rate. It is implemented as feed-forward adapters upon both modalities to alleviate the misalignment problem. Extensive experiments on 15 datasets demonstrate that our method outperforms the state-of-the-art prompt tuning methods without compromising feature alignment.

In this paper, we propose a Vision-Audio-Language Omni-peRception pretraining model (VALOR) for multi-modal understanding and generation. Different from widely-studied vision-language pretraining models, VALOR jointly models relationships of vision, audio and language in an end-to-end manner. It contains three separate encoders for single modality representations, and a decoder for multimodal conditional text generation. We design two pretext tasks to pretrain VALOR model, including Multimodal Grouping Alignment (MGA) and Multimodal Grouping Captioning (MGC). MGA projects vision, language and audio to the same common space, building vision-language, audio-language and audiovisual-language alignment simultaneously. MGC learns how to generate text tokens in conditions of vision, audio or their both. To promote vision-audio-language pretraining research, we construct a large-scale high-quality tri-modality dataset named VALOR-1M, which contains 1M audiable videos with human annotated audiovisual captions. Extensive experiments show that VALOR can learn strong multimodal correlations and be generalized to various downstream tasks (e.g., retrieval, captioning and question answering), with different input modalities (e.g., vision-language, audio-language and audiovisual-language). VALOR achieves new state-of-the-art performances on series of public cross-modality benchmarks. Code and data are available at project page https://casia-iva-group.github.io/projects/VALOR.

Recent one-shot Neural Architecture Search algorithms rely on training a hardware-agnostic super-network tailored to a specific task and then extracting efficient sub-networks for different hardware platforms. Popular approaches separate the training of super-networks from the search for sub-networks, often employing predictors to alleviate the computational overhead associated with search. Additionally, certain methods also incorporate the quantization policy within the search space. However, while the quantization policy search for convolutional neural networks is well studied, the extension of these methods to transformers and especially foundation models remains under-explored. In this paper, we demonstrate that by using multi-objective search algorithms paired with lightly trained predictors, we can efficiently search for both the sub-network architecture and the corresponding quantization policy and outperform their respective baselines across different performance objectives such as accuracy, model size, and latency. Specifically, we demonstrate that our approach performs well across both uni-modal (ViT and BERT) and multi-modal (BEiT-3) transformer-based architectures as well as convolutional architectures (ResNet). For certain networks, we demonstrate an improvement of up to 4.80x and 3.44x for latency and model size respectively, without degradation in accuracy compared to the fully quantized INT8 baselines.

Contrastive learning-based vision-language pre-training approaches, such as CLIP, have demonstrated great success in many vision-language tasks. These methods achieve cross-modal alignment by encoding a matched image-text pair with similar feature embeddings, which are generated by aggregating information from visual patches and language tokens. However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities. To alleviate this issue, we propose a Finite Discrete Tokens (FDT) based multimodal representation. FDT is a set of learnable tokens representing certain visual-semantic concepts. Both images and texts are embedded using shared FDT by first grounding multimodal inputs to FDT space and then aggregating the activated FDT representations. The matched visual and semantic concepts are enforced to be represented by the same set of discrete tokens by a sparse activation constraint. As a result, the granularity gap between the two modalities is reduced. Through both quantitative and qualitative analyses, we demonstrate that using FDT representations in CLIP-style models improves cross-modal alignment and performance in visual recognition and vision-language downstream tasks. Furthermore, we show that our method can learn more comprehensive representations, and the learned FDT capture meaningful cross-modal correspondence, ranging from objects to actions and attributes.

The focal point of egocentric video understanding is modelling hand-object interactions. Standard models, e.g. CNNs or Vision Transformers, which receive RGB frames as input perform well. However, their performance improves further by employing additional input modalities that provide complementary cues, such as object detections, optical flow, audio, etc. The added complexity of the modality-specific modules, on the other hand, makes these models impractical for deployment. The goal of this work is to retain the performance of such a multimodal approach, while using only the RGB frames as input at inference time. We demonstrate that for egocentric action recognition on the Epic-Kitchens and the Something-Something datasets, students which are taught by multimodal teachers tend to be more accurate and better calibrated than architecturally equivalent models trained on ground truth labels in a unimodal or multimodal fashion. We further adopt a principled multimodal knowledge distillation framework, allowing us to deal with issues which occur when applying multimodal knowledge distillation in a naive manner. Lastly, we demonstrate the achieved reduction in computational complexity, and show that our approach maintains higher performance with the reduction of the number of input views. We release our code at https://github.com/gorjanradevski/multimodal-distillation.

Recent advances in audio generation have focused on text-to-audio (T2A) and video-to-audio (V2A) tasks. However, T2A or V2A methods cannot generate holistic sounds (onscreen and off-screen). This is because T2A cannot generate sounds aligning with onscreen objects, while V2A cannot generate semantically complete (offscreen sounds missing). In this work, we address the task of holistic audio generation: given a video and a text prompt, we aim to generate both onscreen and offscreen sounds that are temporally synchronized with the video and semantically aligned with text and video. Previous approaches for joint text and video-to-audio generation often suffer from modality bias, favoring one modality over the other. To overcome this limitation, we introduce VinTAGe, a flow-based transformer model that jointly considers text and video to guide audio generation. Our framework comprises two key components: a Visual-Text Encoder and a Joint VT-SiT model. To reduce modality bias and improve generation quality, we employ pretrained uni-modal text-to-audio and video-to-audio generation models for additional guidance. Due to the lack of appropriate benchmarks, we also introduce VinTAGe-Bench, a dataset of 636 video-text-audio pairs containing both onscreen and offscreen sounds. Our comprehensive experiments on VinTAGe-Bench demonstrate that joint text and visual interaction is necessary for holistic audio generation. Furthermore, VinTAGe achieves state-of-the-art results on the VGGSound benchmark. Our source code and pre-trained models will be released. Demo is available at: https://www.youtube.com/watch?v=QmqWhUjPkJI.

We target cross-domain face reenactment in this paper, i.e., driving a cartoon image with the video of a real person and vice versa. Recently, many works have focused on one-shot talking face generation to drive a portrait with a real video, i.e., within-domain reenactment. Straightforwardly applying those methods to cross-domain animation will cause inaccurate expression transfer, blur effects, and even apparent artifacts due to the domain shift between cartoon and real faces. Only a few works attempt to settle cross-domain face reenactment. The most related work AnimeCeleb requires constructing a dataset with pose vector and cartoon image pairs by animating 3D characters, which makes it inapplicable anymore if no paired data is available. In this paper, we propose a novel method for cross-domain reenactment without paired data. Specifically, we propose a transformer-based framework to align the motions from different domains into a common latent space where motion transfer is conducted via latent code addition. Two domain-specific motion encoders and two learnable motion base memories are used to capture domain properties. A source query transformer and a driving one are exploited to project domain-specific motion to the canonical space. The edited motion is projected back to the domain of the source with a transformer. Moreover, since no paired data is provided, we propose a novel cross-domain training scheme using data from two domains with the designed analogy constraint. Besides, we contribute a cartoon dataset in Disney style. Extensive evaluations demonstrate the superiority of our method over competing methods.

Multimodal large language models (MLLMs) like LLaVA and GPT-4(V) enable general-purpose conversations about images with the language modality. As off-the-shelf MLLMs may have limited capabilities on images from domains like dermatology and agriculture, they must be fine-tuned to unlock domain-specific applications. The prevalent architecture of current open-source MLLMs comprises two major modules: an image-language (cross-modal) projection network and a large language model. It is desirable to understand the roles of these two modules in modeling domain-specific visual attributes to inform the design of future models and streamline the interpretability efforts on the current models. To this end, via experiments on 4 datasets and under 2 fine-tuning settings, we find that as the MLLM is fine-tuned, it indeed gains domain-specific visual capabilities, but the updates do not lead to the projection extracting relevant domain-specific visual attributes. Our results indicate that the domain-specific visual attributes are modeled by the LLM, even when only the projection is fine-tuned. Through this study, we offer a potential reinterpretation of the role of cross-modal projections in MLLM architectures. Projection webpage: https://claws-lab.github.io/projection-in-MLLMs/

The style transfer task in Text-to-Speech refers to the process of transferring style information into text content to generate corresponding speech with a specific style. However, most existing style transfer approaches are either based on fixed emotional labels or reference speech clips, which cannot achieve flexible style transfer. Recently, some methods have adopted text descriptions to guide style transfer. In this paper, we propose a more flexible multi-modal and style controllable TTS framework named MM-TTS. It can utilize any modality as the prompt in unified multi-modal prompt space, including reference speech, emotional facial images, and text descriptions, to control the style of the generated speech in a system. The challenges of modeling such a multi-modal style controllable TTS mainly lie in two aspects:1)aligning the multi-modal information into a unified style space to enable the input of arbitrary modality as the style prompt in a single system, and 2)efficiently transferring the unified style representation into the given text content, thereby empowering the ability to generate prompt style-related voice. To address these problems, we propose an aligned multi-modal prompt encoder that embeds different modalities into a unified style space, supporting style transfer for different modalities. Additionally, we present a new adaptive style transfer method named Style Adaptive Convolutions to achieve a better style representation. Furthermore, we design a Rectified Flow based Refiner to solve the problem of over-smoothing Mel-spectrogram and generate audio of higher fidelity. Since there is no public dataset for multi-modal TTS, we construct a dataset named MEAD-TTS, which is related to the field of expressive talking head. Our experiments on the MEAD-TTS dataset and out-of-domain datasets demonstrate that MM-TTS can achieve satisfactory results based on multi-modal prompts.

We present a unified transformer, i.e., Show-o, that unifies multimodal understanding and generation. Unlike fully autoregressive models, Show-o unifies autoregressive and (discrete) diffusion modeling to adaptively handle inputs and outputs of various and mixed modalities. The unified model flexibly supports a wide range of vision-language tasks including visual question-answering, text-to-image generation, text-guided inpainting/extrapolation, and mixed-modality generation. Across various benchmarks, it demonstrates comparable or superior performance to existing individual models with an equivalent or larger number of parameters tailored for understanding or generation. This significantly highlights its potential as a next-generation foundation model. Code and models are released at https://github.com/showlab/Show-o.

We present a unified formulation and model for three motion and 3D perception tasks: optical flow, rectified stereo matching and unrectified stereo depth estimation from posed images. Unlike previous specialized architectures for each specific task, we formulate all three tasks as a unified dense correspondence matching problem, which can be solved with a single model by directly comparing feature similarities. Such a formulation calls for discriminative feature representations, which we achieve using a Transformer, in particular the cross-attention mechanism. We demonstrate that cross-attention enables integration of knowledge from another image via cross-view interactions, which greatly improves the quality of the extracted features. Our unified model naturally enables cross-task transfer since the model architecture and parameters are shared across tasks. We outperform RAFT with our unified model on the challenging Sintel dataset, and our final model that uses a few additional task-specific refinement steps outperforms or compares favorably to recent state-of-the-art methods on 10 popular flow, stereo and depth datasets, while being simpler and more efficient in terms of model design and inference speed.

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which misses sufficient information, or finer-grained interactions using cross/self-attention upon visual and textual tokens. However, cross/self-attention suffers from inferior efficiency in both training and inference. In this paper, we introduce a large-scale Fine-grained Interactive Language-Image Pre-training (FILIP) to achieve finer-level alignment through a cross-modal late interaction mechanism, which uses a token-wise maximum similarity between visual and textual tokens to guide the contrastive objective. FILIP successfully leverages the finer-grained expressiveness between image patches and textual words by modifying only contrastive loss, while simultaneously gaining the ability to pre-compute image and text representations offline at inference, keeping both large-scale training and inference efficient. Furthermore, we construct a new large-scale image-text pair dataset called FILIP300M for pre-training. Experiments show that FILIP achieves state-of-the-art performance on multiple downstream vision-language tasks including zero-shot image classification and image-text retrieval. The visualization on word-patch alignment further shows that FILIP can learn meaningful fine-grained features with promising localization ability.

With the rapid advances in high-throughput sequencing technologies, the focus of survival analysis has shifted from examining clinical indicators to incorporating genomic profiles with pathological images. However, existing methods either directly adopt a straightforward fusion of pathological features and genomic profiles for survival prediction, or take genomic profiles as guidance to integrate the features of pathological images. The former would overlook intrinsic cross-modal correlations. The latter would discard pathological information irrelevant to gene expression. To address these issues, we present a Cross-Modal Translation and Alignment (CMTA) framework to explore the intrinsic cross-modal correlations and transfer potential complementary information. Specifically, we construct two parallel encoder-decoder structures for multi-modal data to integrate intra-modal information and generate cross-modal representation. Taking the generated cross-modal representation to enhance and recalibrate intra-modal representation can significantly improve its discrimination for comprehensive survival analysis. To explore the intrinsic crossmodal correlations, we further design a cross-modal attention module as the information bridge between different modalities to perform cross-modal interactions and transfer complementary information. Our extensive experiments on five public TCGA datasets demonstrate that our proposed framework outperforms the state-of-the-art methods.

The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction. To fully release the value of each modality and mitigate the influence of low-quality multimodal data, dynamic multimodal fusion emerges as a promising learning paradigm. Despite its widespread use, theoretical justifications in this field are still notably lacking. Can we design a provably robust multimodal fusion method? This paper provides theoretical understandings to answer this question under a most popular multimodal fusion framework from the generalization perspective. We proceed to reveal that several uncertainty estimation solutions are naturally available to achieve robust multimodal fusion. Then a novel multimodal fusion framework termed Quality-aware Multimodal Fusion (QMF) is proposed, which can improve the performance in terms of classification accuracy and model robustness. Extensive experimental results on multiple benchmarks can support our findings.

A common practice in deep learning involves training large neural networks on massive datasets to achieve high accuracy across various domains and tasks. While this approach works well in many application areas, it often fails drastically when processing data from a new modality with a significant distribution shift from the data used to pre-train the model. This paper focuses on adapting a large object detection model trained on RGB images to new data extracted from IR images with a substantial modality shift. We propose Modality Translator (ModTr) as an alternative to the common approach of fine-tuning a large model to the new modality. ModTr adapts the IR input image with a small transformation network trained to directly minimize the detection loss. The original RGB model can then work on the translated inputs without any further changes or fine-tuning to its parameters. Experimental results on translating from IR to RGB images on two well-known datasets show that our simple approach provides detectors that perform comparably or better than standard fine-tuning, without forgetting the knowledge of the original model. This opens the door to a more flexible and efficient service-based detection pipeline, where a unique and unaltered server, such as an RGB detector, runs constantly while being queried by different modalities, such as IR with the corresponding translations model. Our code is available at: https://github.com/heitorrapela/ModTr.

Humans can easily perceive the direction of sound sources in a visual scene, termed sound source localization. Recent studies on learning-based sound source localization have mainly explored the problem from a localization perspective. However, prior arts and existing benchmarks do not account for a more important aspect of the problem, cross-modal semantic understanding, which is essential for genuine sound source localization. Cross-modal semantic understanding is important in understanding semantically mismatched audio-visual events, e.g., silent objects, or off-screen sounds. To account for this, we propose a cross-modal alignment task as a joint task with sound source localization to better learn the interaction between audio and visual modalities. Thereby, we achieve high localization performance with strong cross-modal semantic understanding. Our method outperforms the state-of-the-art approaches in both sound source localization and cross-modal retrieval. Our work suggests that jointly tackling both tasks is necessary to conquer genuine sound source localization.

Transformer-based methods have shown impressive performance in image restoration tasks, such as image super-resolution and denoising. However, we find that these networks can only utilize a limited spatial range of input information through attribution analysis. This implies that the potential of Transformer is still not fully exploited in existing networks. In order to activate more input pixels for better restoration, we propose a new Hybrid Attention Transformer (HAT). It combines both channel attention and window-based self-attention schemes, thus making use of their complementary advantages. Moreover, to better aggregate the cross-window information, we introduce an overlapping cross-attention module to enhance the interaction between neighboring window features. In the training stage, we additionally adopt a same-task pre-training strategy to further exploit the potential of the model for further improvement. Extensive experiments have demonstrated the effectiveness of the proposed modules. We further scale up the model to show that the performance of the SR task can be greatly improved. Besides, we extend HAT to more image restoration applications, including real-world image super-resolution, Gaussian image denoising and image compression artifacts reduction. Experiments on benchmark and real-world datasets demonstrate that our HAT achieves state-of-the-art performance both quantitatively and qualitatively. Codes and models are publicly available at https://github.com/XPixelGroup/HAT.

Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We present CrossOver, a novel framework for cross-modal 3D scene understanding via flexible, scene-level modality alignment. Unlike traditional methods that require aligned modality data for every object instance, CrossOver learns a unified, modality-agnostic embedding space for scenes by aligning modalities - RGB images, point clouds, CAD models, floorplans, and text descriptions - with relaxed constraints and without explicit object semantics. Leveraging dimensionality-specific encoders, a multi-stage training pipeline, and emergent cross-modal behaviors, CrossOver supports robust scene retrieval and object localization, even with missing modalities. Evaluations on ScanNet and 3RScan datasets show its superior performance across diverse metrics, highlighting adaptability for real-world applications in 3D scene understanding.

Multimodal entity linking (MEL) aims to link ambiguous mentions within multimodal contexts to corresponding entities in a multimodal knowledge base. Most existing approaches to MEL are based on representation learning or vision-and-language pre-training mechanisms for exploring the complementary effect among multiple modalities. However, these methods suffer from two limitations. On the one hand, they overlook the possibility of considering negative samples from the same modality. On the other hand, they lack mechanisms to capture bidirectional cross-modal interaction. To address these issues, we propose a Multi-level Matching network for Multimodal Entity Linking (M3EL). Specifically, M3EL is composed of three different modules: (i) a Multimodal Feature Extraction module, which extracts modality-specific representations with a multimodal encoder and introduces an intra-modal contrastive learning sub-module to obtain better discriminative embeddings based on uni-modal differences; (ii) an Intra-modal Matching Network module, which contains two levels of matching granularity: Coarse-grained Global-to-Global and Fine-grained Global-to-Local, to achieve local and global level intra-modal interaction; (iii) a Cross-modal Matching Network module, which applies bidirectional strategies, Textual-to-Visual and Visual-to-Textual matching, to implement bidirectional cross-modal interaction. Extensive experiments conducted on WikiMEL, RichpediaMEL, and WikiDiverse datasets demonstrate the outstanding performance of M3EL when compared to the state-of-the-art baselines.

We present FIND, a generalized interface for aligning foundation models' embeddings. As shown in teaser figure, a lightweight transformer interface without tuning any foundation model weights is enough for a unified image (segmentation) and dataset-level (retrieval) understanding. The proposed interface has the following favorable attributes: (1) Generalizable. It applies to various tasks spanning retrieval, segmentation, etc., under the same architecture and weights. (2) Prototypable. Different tasks are able to be implemented through prototyping attention masks and embedding types. (3) Extendable. The proposed interface is adaptive to new tasks, and new models. (4) Interleavable. With the benefit of multi-task multi-modal training, the proposed interface creates an interleaved shared embedding space. In light of the interleaved embedding space, we introduce the FIND-Bench, which introduces new training and evaluation annotations to the COCO dataset for interleave segmentation and retrieval. Our approach achieves state-of-the-art performance on FIND-Bench and competitive performance on standard retrieval and segmentation settings. The training, evaluation, and demo code as well as the dataset have been released at https://github.com/UX-Decoder/FIND.

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as joint speech-text encoders that can scale to the capacities of very large parameter models by being trained on both unpaired speech and text. While these methods show promise, they have required special treatment of the sequence-length mismatch inherent in speech and text, either by up-sampling heuristics or an explicit alignment model. In this work, we offer evidence that joint speech-text encoders naturally achieve consistent representations across modalities by disregarding sequence length, and argue that consistency losses could forgive length differences and simply assume the best alignment. We show that such a loss improves downstream WER in both a large-parameter monolingual and multilingual system.

Scene understanding using multi-modal data is necessary in many applications, e.g., autonomous navigation. To achieve this in a variety of situations, existing models must be able to adapt to shifting data distributions without arduous data annotation. Current approaches assume that the source data is available during adaptation and that the source consists of paired multi-modal data. Both these assumptions may be problematic for many applications. Source data may not be available due to privacy, security, or economic concerns. Assuming the existence of paired multi-modal data for training also entails significant data collection costs and fails to take advantage of widely available freely distributed pre-trained uni-modal models. In this work, we relax both of these assumptions by addressing the problem of adapting a set of models trained independently on uni-modal data to a target domain consisting of unlabeled multi-modal data, without having access to the original source dataset. Our proposed approach solves this problem through a switching framework which automatically chooses between two complementary methods of cross-modal pseudo-label fusion -- agreement filtering and entropy weighting -- based on the estimated domain gap. We demonstrate our work on the semantic segmentation problem. Experiments across seven challenging adaptation scenarios verify the efficacy of our approach, achieving results comparable to, and in some cases outperforming, methods which assume access to source data. Our method achieves an improvement in mIoU of up to 12% over competing baselines. Our code is publicly available at https://github.com/csimo005/SUMMIT.

Recently, an audio-visual segmentation (AVS) task has been introduced, aiming to group pixels with sounding objects within a given video. This task necessitates a first-ever audio-driven pixel-level understanding of the scene, posing significant challenges. In this paper, we propose an innovative audio-visual transformer framework, termed COMBO, an acronym for COoperation of Multi-order Bilateral relatiOns. For the first time, our framework explores three types of bilateral entanglements within AVS: pixel entanglement, modality entanglement, and temporal entanglement. Regarding pixel entanglement, we employ a Siam-Encoder Module (SEM) that leverages prior knowledge to generate more precise visual features from the foundational model. For modality entanglement, we design a Bilateral-Fusion Module (BFM), enabling COMBO to align corresponding visual and auditory signals bi-directionally. As for temporal entanglement, we introduce an innovative adaptive inter-frame consistency loss according to the inherent rules of temporal. Comprehensive experiments and ablation studies on AVSBench-object (84.7 mIoU on S4, 59.2 mIou on MS3) and AVSBench-semantic (42.1 mIoU on AVSS) datasets demonstrate that COMBO surpasses previous state-of-the-art methods. Code and more results will be publicly available at https://combo-avs.github.io/.

Referring Image Segmentation~(RIS) leveraging transformers has achieved great success on the interpretation of complex visual-language tasks. However, the quadratic computation cost makes it resource-consuming in capturing long-range visual-language dependencies. Fortunately, Mamba addresses this with efficient linear complexity in processing. However, directly applying Mamba to multi-modal interactions presents challenges, primarily due to inadequate channel interactions for the effective fusion of multi-modal data. In this paper, we propose ReMamber, a novel RIS architecture that integrates the power of Mamba with a multi-modal Mamba Twister block. The Mamba Twister explicitly models image-text interaction, and fuses textual and visual features through its unique channel and spatial twisting mechanism. We achieve competitive results on three challenging benchmarks with a simple and efficient architecture. Moreover, we conduct thorough analyses of ReMamber and discuss other fusion designs using Mamba. These provide valuable perspectives for future research. The code has been released at: https://github.com/yyh-rain-song/ReMamber.

Visual grounding, which aims to ground a visual region via natural language, is a task that heavily relies on cross-modal alignment. Existing works utilized uni-modal pre-trained models to transfer visual/linguistic knowledge separately while ignoring the multimodal corresponding information. Motivated by recent advancements in contrastive language-image pre-training and low-rank adaptation (LoRA) methods, we aim to solve the grounding task based on multimodal pre-training. However, there exists significant task gaps between pre-training and grounding. Therefore, to address these gaps, we propose a concise and efficient hierarchical multimodal fine-grained modulation framework, namely HiVG. Specifically, HiVG consists of a multi-layer adaptive cross-modal bridge and a hierarchical multimodal low-rank adaptation (Hi LoRA) paradigm. The cross-modal bridge can address the inconsistency between visual features and those required for grounding, and establish a connection between multi-level visual and text features. Hi LoRA prevents the accumulation of perceptual errors by adapting the cross-modal features from shallow to deep layers in a hierarchical manner. Experimental results on five datasets demonstrate the effectiveness of our approach and showcase the significant grounding capabilities as well as promising energy efficiency advantages. The project page: https://github.com/linhuixiao/HiVG.

There is increasing interest in the use of multimodal data in various web applications, such as digital advertising and e-commerce. Typical methods for extracting important information from multimodal data rely on a mid-fusion architecture that combines the feature representations from multiple encoders. However, as the number of modalities increases, several potential problems with the mid-fusion model structure arise, such as an increase in the dimensionality of the concatenated multimodal features and missing modalities. To address these problems, we propose a new concept that considers multimodal inputs as a set of sequences, namely, deep multimodal sequence sets (DM^2S^2). Our set-aware concept consists of three components that capture the relationships among multiple modalities: (a) a BERT-based encoder to handle the inter- and intra-order of elements in the sequences, (b) intra-modality residual attention (IntraMRA) to capture the importance of the elements in a modality, and (c) inter-modality residual attention (InterMRA) to enhance the importance of elements with modality-level granularity further. Our concept exhibits performance that is comparable to or better than the previous set-aware models. Furthermore, we demonstrate that the visualization of the learned InterMRA and IntraMRA weights can provide an interpretation of the prediction results.

Currently, one main research line in designing a more efficient vision transformer is reducing the computational cost of self attention modules by adopting sparse attention or using local attention windows. In contrast, we propose a different approach that aims to improve the performance of transformer-based architectures by densifying the attention pattern. Specifically, we proposed forward cross attention for hybrid vision transformer (FcaFormer), where tokens from previous blocks in the same stage are secondary used. To achieve this, the FcaFormer leverages two innovative components: learnable scale factors (LSFs) and a token merge and enhancement module (TME). The LSFs enable efficient processing of cross tokens, while the TME generates representative cross tokens. By integrating these components, the proposed FcaFormer enhances the interactions of tokens across blocks with potentially different semantics, and encourages more information flows to the lower levels. Based on the forward cross attention (Fca), we have designed a series of FcaFormer models that achieve the best trade-off between model size, computational cost, memory cost, and accuracy. For example, without the need for knowledge distillation to strengthen training, our FcaFormer achieves 83.1% top-1 accuracy on Imagenet with only 16.3 million parameters and about 3.6 billion MACs. This saves almost half of the parameters and a few computational costs while achieving 0.7% higher accuracy compared to distilled EfficientFormer.

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT) and Reinforcement Learning with Human Feedback (RLHF). While further SFT and RLHF-based safety training can be conducted in multi-modal settings, collecting multi-modal training datasets poses a significant challenge. Inspired by the structural design of recent multi-modal models, where, regardless of the combination of input modalities, all inputs are ultimately fused into the language space, we aim to explore whether unlearning solely in the textual domain can be effective for cross-modality safety alignment. Our evaluation across six datasets empirically demonstrates the transferability -- textual unlearning in VLMs significantly reduces the Attack Success Rate (ASR) to less than 8\% and in some cases, even as low as nearly 2\% for both text-based and vision-text-based attacks, alongside preserving the utility. Moreover, our experiments show that unlearning with a multi-modal dataset offers no potential benefits but incurs significantly increased computational demands, possibly up to 6 times higher.

Medical vision-and-language pre-training (Med-VLP) has shown promising improvements on many downstream medical tasks owing to its applicability to extracting generic representations from medical images and texts. Practically, there exist two typical types, i.e., the fusion-encoder type and the dual-encoder type, depending on whether a heavy fusion module is used. The former is superior at multi-modal tasks owing to the sufficient interaction between modalities; the latter is good at uni-modal and cross-modal tasks due to the single-modality encoding ability. To take advantage of these two types, we propose an effective yet straightforward scheme named PTUnifier to unify the two types. We first unify the input format by introducing visual and textual prompts, which serve as a feature bank that stores the most representative images/texts. By doing so, a single model could serve as a foundation model that processes various tasks adopting different input formats (i.e., image-only, text-only, and image-text-pair). Furthermore, we construct a prompt pool (instead of static ones) to improve diversity and scalability. Experimental results show that our approach achieves state-of-the-art results on a broad range of tasks, spanning uni-modal tasks (i.e., image/text classification and text summarization), cross-modal tasks (i.e., image-to-text generation and image-text/text-image retrieval), and multi-modal tasks (i.e., visual question answering), demonstrating the effectiveness of our approach. Note that the adoption of prompts is orthogonal to most existing Med-VLP approaches and could be a beneficial and complementary extension to these approaches.

In this work, we build a simple but strong baseline for sounding video generation. Given base diffusion models for audio and video, we integrate them with additional modules into a single model and train it to make the model jointly generate audio and video. To enhance alignment between audio-video pairs, we introduce two novel mechanisms in our model. The first one is timestep adjustment, which provides different timestep information to each base model. It is designed to align how samples are generated along with timesteps across modalities. The second one is a new design of the additional modules, termed Cross-Modal Conditioning as Positional Encoding (CMC-PE). In CMC-PE, cross-modal information is embedded as if it represents temporal position information, and the embeddings are fed into the model like positional encoding. Compared with the popular cross-attention mechanism, CMC-PE provides a better inductive bias for temporal alignment in the generated data. Experimental results validate the effectiveness of the two newly introduced mechanisms and also demonstrate that our method outperforms existing methods.

Transformers can capture long-range dependencies using self-attention, allowing tokens to attend to all others directly. However, stacking multiple attention layers leads to attention concentration. One natural way to address this issue is to use cross-layer attention, allowing information from earlier layers to be directly accessible to later layers. However, this approach is computationally expensive. To address this problem, we propose Transformer with residual value (ResFormer) which approximates cross-layer attention through adding a residual connection from the values of the the first layer to all subsequent layers. Based on this method, one variant is the Transformer with single layer value (SVFormer), where all layers share the same value embedding from first layer, reducing the KV cache by nearly 50%. Comprehensive empirical evidence demonstrates that ResFormer mitigates attention concentration problem in deeper layers and enhances representation across most layers, outperforming the vanilla Transformer, DenseFormer, and NeuTRENO in training error as well as downstream tasks. SVFormer trains significantly faster than the vanilla Transformer and performs better than other methods like GQA and CLA, with performance influenced by sequence length and cumulative learning rate.

Speech-driven 3D facial animation has improved a lot recently while most related works only utilize acoustic modality and neglect the influence of visual and textual cues, leading to unsatisfactory results in terms of precision and coherence. We argue that visual and textual cues are not trivial information. Therefore, we present a novel framework, namely PMMTalk, using complementary Pseudo Multi-Modal features for improving the accuracy of facial animation. The framework entails three modules: PMMTalk encoder, cross-modal alignment module, and PMMTalk decoder. Specifically, the PMMTalk encoder employs the off-the-shelf talking head generation architecture and speech recognition technology to extract visual and textual information from speech, respectively. Subsequently, the cross-modal alignment module aligns the audio-image-text features at temporal and semantic levels. Then PMMTalk decoder is employed to predict lip-syncing facial blendshape coefficients. Contrary to prior methods, PMMTalk only requires an additional random reference face image but yields more accurate results. Additionally, it is artist-friendly as it seamlessly integrates into standard animation production workflows by introducing facial blendshape coefficients. Finally, given the scarcity of 3D talking face datasets, we introduce a large-scale 3D Chinese Audio-Visual Facial Animation (3D-CAVFA) dataset. Extensive experiments and user studies show that our approach outperforms the state of the art. We recommend watching the supplementary video.

In this work, we extend the instruction-tuned Llama-2 model with end-to-end general-purpose speech processing and reasoning abilities while maintaining the wide range of LLM capabilities, without using any carefully curated paired data. The proposed model can utilize audio prompts as a replacement for text and sustain a conversation. Such a model also has extended cross-modal capabilities such as being able to perform speech question answering, speech translation, and audio summarization amongst many other closed and open-domain tasks. This is unlike prior approaches in speech, in which LLMs are extended to handle audio for a limited number of pre-designated tasks. Experiments show that our end-to-end approach is on par with or outperforms a cascaded system (speech recognizer + LLM) in terms of modeling the response to a prompt. Furthermore, unlike a cascade, our approach shows the ability to interchange text and audio modalities and utilize the prior context in a conversation to provide better results.

Multi-modal models have shown a promising capability to effectively integrate information from various sources, yet meanwhile, they are found vulnerable to pervasive perturbations, such as uni-modal attacks and missing conditions. To counter these perturbations, robust multi-modal representations are highly expected, which are positioned well away from the discriminative multi-modal decision boundary. In this paper, different from conventional empirical studies, we focus on a commonly used joint multi-modal framework and theoretically discover that larger uni-modal representation margins and more reliable integration for modalities are essential components for achieving higher robustness. This discovery can further explain the limitation of multi-modal robustness and the phenomenon that multi-modal models are often vulnerable to attacks on the specific modality. Moreover, our analysis reveals how the widespread issue, that the model has different preferences for modalities, limits the multi-modal robustness by influencing the essential components and could lead to attacks on the specific modality highly effective. Inspired by our theoretical finding, we introduce a training procedure called Certifiable Robust Multi-modal Training (CRMT), which can alleviate this influence from modality preference and explicitly regulate essential components to significantly improve robustness in a certifiable manner. Our method demonstrates substantial improvements in performance and robustness compared with existing methods. Furthermore, our training procedure can be easily extended to enhance other robust training strategies, highlighting its credibility and flexibility.

This work uniquely identifies and characterizes four prevalent multimodal model architectural patterns in the contemporary multimodal landscape. Systematically categorizing models by architecture type facilitates monitoring of developments in the multimodal domain. Distinct from recent survey papers that present general information on multimodal architectures, this research conducts a comprehensive exploration of architectural details and identifies four specific architectural types. The types are distinguished by their respective methodologies for integrating multimodal inputs into the deep neural network model. The first two types (Type A and B) deeply fuses multimodal inputs within the internal layers of the model, whereas the following two types (Type C and D) facilitate early fusion at the input stage. Type-A employs standard cross-attention, whereas Type-B utilizes custom-designed layers for modality fusion within the internal layers. On the other hand, Type-C utilizes modality-specific encoders, while Type-D leverages tokenizers to process the modalities at the model's input stage. The identified architecture types aid the monitoring of any-to-any multimodal model development. Notably, Type-C and Type-D are currently favored in the construction of any-to-any multimodal models. Type-C, distinguished by its non-tokenizing multimodal model architecture, is emerging as a viable alternative to Type-D, which utilizes input-tokenizing techniques. To assist in model selection, this work highlights the advantages and disadvantages of each architecture type based on data and compute requirements, architecture complexity, scalability, simplification of adding modalities, training objectives, and any-to-any multimodal generation capability.

Transformers have emerged as a preferred model for many tasks in natural langugage processing and vision. Recent efforts on training and deploying Transformers more efficiently have identified many strategies to approximate the self-attention matrix, a key module in a Transformer architecture. Effective ideas include various prespecified sparsity patterns, low-rank basis expansions and combinations thereof. In this paper, we revisit classical Multiresolution Analysis (MRA) concepts such as Wavelets, whose potential value in this setting remains underexplored thus far. We show that simple approximations based on empirical feedback and design choices informed by modern hardware and implementation challenges, eventually yield a MRA-based approach for self-attention with an excellent performance profile across most criteria of interest. We undertake an extensive set of experiments and demonstrate that this multi-resolution scheme outperforms most efficient self-attention proposals and is favorable for both short and long sequences. Code is available at https://github.com/mlpen/mra-attention.

GPT-4o, an all-encompassing model, represents a milestone in the development of large multi-modal language models. It can understand visual, auditory, and textual modalities, directly output audio, and support flexible duplex interaction. Models from the open-source community often achieve some functionalities of GPT-4o, such as visual understanding and voice chat. Nevertheless, training a unified model that incorporates all modalities is challenging due to the complexities of multi-modal data, intricate model architectures, and training processes. In this paper, we introduce Mini-Omni2, a visual-audio assistant capable of providing real-time, end-to-end voice responses to visoin and audio queries. By integrating pretrained visual and auditory encoders, Mini-Omni2 maintains performance in individual modalities. We propose a three-stage training process to align modalities, allowing the language model to handle multi-modal inputs and outputs after training on a limited dataset. For interaction, we introduce a command-based interruption mechanism, enabling more flexible interaction with users. To the best of our knowledge, Mini-Omni2 is one of the closest reproductions of GPT-4o, which have similar form of functionality, and we hope it can offer valuable insights for subsequent research.

Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.

Recently, the success of pre-training in text domain has been fully extended to vision, audio, and cross-modal scenarios. The proposed pre-training models of different modalities are showing a rising trend of homogeneity in their model structures, which brings the opportunity to implement different pre-training models within a uniform framework. In this paper, we present TencentPretrain, a toolkit supporting pre-training models of different modalities. The core feature of TencentPretrain is the modular design. The toolkit uniformly divides pre-training models into 5 components: embedding, encoder, target embedding, decoder, and target. As almost all of common modules are provided in each component, users can choose the desired modules from different components to build a complete pre-training model. The modular design enables users to efficiently reproduce existing pre-training models or build brand-new one. We test the toolkit on text, vision, and audio benchmarks and show that it can match the performance of the original implementations.

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer pre-trained solely by one unified pre-training task. Specifically, EVE encodes both vision and language within a shared Transformer network integrated with modality-aware sparse Mixture-of-Experts (MoE) modules, which capture modality-specific information by selectively switching to different experts. To unify pre-training tasks of vision and language, EVE performs masked signal modeling on image-text pairs to reconstruct masked signals, i.e., image pixels and text tokens, given visible signals. This simple yet effective pre-training objective accelerates training by 3.5x compared to the model pre-trained with Image-Text Contrastive and Image-Text Matching losses. Owing to the combination of the unified architecture and pre-training task, EVE is easy to scale up, enabling better downstream performance with fewer resources and faster training speed. Despite its simplicity, EVE achieves state-of-the-art performance on various vision-language downstream tasks, including visual question answering, visual reasoning, and image-text retrieval.

Image matching, which aims to identify corresponding pixel locations between images, is crucial in a wide range of scientific disciplines, aiding in image registration, fusion, and analysis. In recent years, deep learning-based image matching algorithms have dramatically outperformed humans in rapidly and accurately finding large amounts of correspondences. However, when dealing with images captured under different imaging modalities that result in significant appearance changes, the performance of these algorithms often deteriorates due to the scarcity of annotated cross-modal training data. This limitation hinders applications in various fields that rely on multiple image modalities to obtain complementary information. To address this challenge, we propose a large-scale pre-training framework that utilizes synthetic cross-modal training signals, incorporating diverse data from various sources, to train models to recognize and match fundamental structures across images. This capability is transferable to real-world, unseen cross-modality image matching tasks. Our key finding is that the matching model trained with our framework achieves remarkable generalizability across more than eight unseen cross-modality registration tasks using the same network weight, substantially outperforming existing methods, whether designed for generalization or tailored for specific tasks. This advancement significantly enhances the applicability of image matching technologies across various scientific disciplines and paves the way for new applications in multi-modality human and artificial intelligence analysis and beyond.

While behavior learning has made impressive progress in recent times, it lags behind computer vision and natural language processing due to its inability to leverage large, human-generated datasets. Human behaviors have wide variance, multiple modes, and human demonstrations typically do not come with reward labels. These properties limit the applicability of current methods in Offline RL and Behavioral Cloning to learn from large, pre-collected datasets. In this work, we present Behavior Transformer (BeT), a new technique to model unlabeled demonstration data with multiple modes. BeT retrofits standard transformer architectures with action discretization coupled with a multi-task action correction inspired by offset prediction in object detection. This allows us to leverage the multi-modal modeling ability of modern transformers to predict multi-modal continuous actions. We experimentally evaluate BeT on a variety of robotic manipulation and self-driving behavior datasets. We show that BeT significantly improves over prior state-of-the-art work on solving demonstrated tasks while capturing the major modes present in the pre-collected datasets. Finally, through an extensive ablation study, we analyze the importance of every crucial component in BeT. Videos of behavior generated by BeT are available at https://notmahi.github.io/bet

Recently, there has been an increasing focus on audio-text cross-modal learning. However, most of the existing audio-text datasets contain only simple descriptions of sound events. Compared with classification labels, the advantages of such descriptions are significantly limited. In this paper, we first analyze the detailed information that human descriptions of audio may contain beyond sound event labels. Based on the analysis, we propose an automatic pipeline for curating audio-text pairs with rich details. Leveraging the property that sounds can be mixed and concatenated in the time domain, we control details in four aspects: temporal relationship, loudness, speaker identity, and occurrence number, in simulating audio mixtures. Corresponding details are transformed into captions by large language models. Audio-text pairs with rich details in text descriptions are thereby obtained. We validate the effectiveness of our pipeline with a small amount of simulated data, demonstrating that the simulated data enables models to learn detailed audio captioning.

Standard multi-modal models assume the use of the same modalities in training and inference stages. However, in practice, the environment in which multi-modal models operate may not satisfy such assumption. As such, their performances degrade drastically if any modality is missing in the inference stage. We ask: how can we train a model that is robust to missing modalities? This paper seeks a set of good practices for multi-modal action recognition, with a particular interest in circumstances where some modalities are not available at an inference time. First, we study how to effectively regularize the model during training (e.g., data augmentation). Second, we investigate on fusion methods for robustness to missing modalities: we find that transformer-based fusion shows better robustness for missing modality than summation or concatenation. Third, we propose a simple modular network, ActionMAE, which learns missing modality predictive coding by randomly dropping modality features and tries to reconstruct them with the remaining modality features. Coupling these good practices, we build a model that is not only effective in multi-modal action recognition but also robust to modality missing. Our model achieves the state-of-the-arts on multiple benchmarks and maintains competitive performances even in missing modality scenarios. Codes are available at https://github.com/sangminwoo/ActionMAE.

Large pre-trained vision-language models, such as CLIP, have demonstrated state-of-the-art performance across a wide range of image classification tasks, without requiring retraining. Few-shot CLIP is competitive with existing specialized architectures that were trained on the downstream tasks. Recent research demonstrates that the performance of CLIP can be further improved using lightweight adaptation approaches. However, previous methods adapt different modalities of the CLIP model individually, ignoring the interactions and relationships between visual and textual representations. In this work, we propose Multi-Modal Adapter, an approach for Multi-Modal adaptation of CLIP. Specifically, we add a trainable Multi-Head Attention layer that combines text and image features to produce an additive adaptation of both. Multi-Modal Adapter demonstrates improved generalizability, based on its performance on unseen classes compared to existing adaptation methods. We perform additional ablations and investigations to validate and interpret the proposed approach.

Human beings perceive the real world through a spectrum of sensory modalities, encompassing auditory, visual, and linguistic faculties. The journey towards achieving Artificial General Intelligence (AGI) necessitates the development of models that can emulate these multifaceted perceptual capabilities and comprehensively understand these diversified data. To this end, we introduce Nexus-O, an industry-level omni-perceptive and -interactive model capable of efficiently processing Audio, Image, Video, and Text data in any combination and output audio/text in an end-to-end way. We systematically investigate Nexus-O by addressing three key research questions: First, how can models be efficiently designed and trained to achieve tri-modal alignment, understanding and reasoning capabilities across multiple modalities? Second, what approaches can be implemented to evaluate tri-modal model robustness, ensuring reliable performance and applicability in real-world scenarios? Third, what strategies can be employed to curate and obtain high-quality, real-life scenario speech datasets? For the first question, we design and pre-train Nexus-O based on the vision-language model, rather than the language model. By pre-training the model over high-quality synthetic audio data, our model is capable of tri-modal perception and interaction. For the second question, we introduce a new audio testbed, Nexus-O-audio, comprising diverse Automatic Speech Recognition (ASR) samples, spanning various real-world scenarios, such as corporate meetings and live stream. For the third question, we design the speech data synthesis pipeline to obtain high-quality speech training datasets, covering various real-world scenarios. Comprehensive experimentation and an in-depth analysis of tri-modal alignment over latent space demonstrate the advantages of our model on downstream tasks.

Modern high-scoring models of vision in the brain score competition do not stem from Vision Transformers. However, in this paper, we provide evidence against the unexpected trend of Vision Transformers (ViT) being not perceptually aligned with human visual representations by showing how a dual-stream Transformer, a CrossViT~a la Chen et al. (2021), under a joint rotationally-invariant and adversarial optimization procedure yields 2nd place in the aggregate Brain-Score 2022 competition(Schrimpf et al., 2020b) averaged across all visual categories, and at the time of the competition held 1st place for the highest explainable variance of area V4. In addition, our current Transformer-based model also achieves greater explainable variance for areas V4, IT and Behaviour than a biologically-inspired CNN (ResNet50) that integrates a frontal V1-like computation module (Dapello et al.,2020). To assess the contribution of the optimization scheme with respect to the CrossViT architecture, we perform several additional experiments on differently optimized CrossViT's regarding adversarial robustness, common corruption benchmarks, mid-ventral stimuli interpretation and feature inversion. Against our initial expectations, our family of results provides tentative support for an "All roads lead to Rome" argument enforced via a joint optimization rule even for non biologically-motivated models of vision such as Vision Transformers. Code is available at https://github.com/williamberrios/BrainScore-Transformers

The remarkable success of transformers in the field of natural language processing has sparked the interest of the speech-processing community, leading to an exploration of their potential for modeling long-range dependencies within speech sequences. Recently, transformers have gained prominence across various speech-related domains, including automatic speech recognition, speech synthesis, speech translation, speech para-linguistics, speech enhancement, spoken dialogue systems, and numerous multimodal applications. In this paper, we present a comprehensive survey that aims to bridge research studies from diverse subfields within speech technology. By consolidating findings from across the speech technology landscape, we provide a valuable resource for researchers interested in harnessing the power of transformers to advance the field. We identify the challenges encountered by transformers in speech processing while also offering insights into potential solutions to address these issues.

Multimodal Large Language Models have made significant strides in integrating visual and textual information, yet they often struggle with effectively aligning these modalities. We introduce a novel image tokenizer that bridges this gap by applying the principle of Byte-Pair Encoding (BPE) to visual data. Unlike conventional approaches that rely on separate visual encoders, our method directly incorporates structural prior information into image tokens, mirroring the successful tokenization strategies used in text-only Large Language Models. This innovative approach enables Transformer models to more effectively learn and reason across modalities. Through theoretical analysis and extensive experiments, we demonstrate that our BPE Image Tokenizer significantly enhances MLLMs' multimodal understanding capabilities, even with limited training data. Our method not only improves performance across various benchmarks but also shows promising scalability, potentially paving the way for more efficient and capable multimodal foundation models.

Video summarization has become an increasingly important task in the field of computer vision due to the vast amount of video content available on the internet. In this project, we propose a new method for natural language query based joint video summarization and highlight detection using multi-modal transformers. This approach will use both visual and audio cues to match a user's natural language query to retrieve the most relevant and interesting moments from a video. Our approach employs multiple recent techniques used in Vision Transformers (ViTs) to create a transformer-like encoder-decoder model. We evaluated our approach on multiple datasets such as YouTube Highlights and TVSum to demonstrate the flexibility of our proposed method.

Multimodal large-scale pretraining has shown impressive performance gains for unstructured data including language, image, audio, and video. Yet, the scenario most prominent in real-world applications is the existence of combination of structured (including tabular and time-series) and unstructured data, and this has so far been understudied. Towards this end, we propose LANISTR, a novel attention-based framework to learn from LANguage, Image, and STRuctured data. We introduce a new multimodal fusion module with a similarity-based multimodal masking loss that enables LANISTR to learn cross-modal relations from large-scale multimodal data with missing modalities during training and test time. On two publicly available challenging datasets, MIMIC-IV and Amazon Product Review, LANISTR achieves absolute improvements of 6.47% (AUROC) and up to 17.69% (accuracy), respectively, compared to the state-of-the-art multimodal models while showing superior generalization capabilities.

Text-to-video (T2V) generation has recently garnered significant attention thanks to the large multi-modality model Sora. However, T2V generation still faces two important challenges: 1) Lacking a precise open sourced high-quality dataset. The previous popular video datasets, e.g. WebVid-10M and Panda-70M, are either with low quality or too large for most research institutions. Therefore, it is challenging but crucial to collect a precise high-quality text-video pairs for T2V generation. 2) Ignoring to fully utilize textual information. Recent T2V methods have focused on vision transformers, using a simple cross attention module for video generation, which falls short of thoroughly extracting semantic information from text prompt. To address these issues, we introduce OpenVid-1M, a precise high-quality dataset with expressive captions. This open-scenario dataset contains over 1 million text-video pairs, facilitating research on T2V generation. Furthermore, we curate 433K 1080p videos from OpenVid-1M to create OpenVidHD-0.4M, advancing high-definition video generation. Additionally, we propose a novel Multi-modal Video Diffusion Transformer (MVDiT) capable of mining both structure information from visual tokens and semantic information from text tokens. Extensive experiments and ablation studies verify the superiority of OpenVid-1M over previous datasets and the effectiveness of our MVDiT.

Multimodal Large Language Models (MLLMs) demonstrate remarkable image-language capabilities, but their widespread use faces challenges in cost-effective training and adaptation. Existing approaches often necessitate expensive language model retraining and limited adaptability. Additionally, the current focus on zero-shot performance improvements offers insufficient guidance for task-specific tuning. We propose CROME, an efficient vision-language instruction tuning framework. It features a novel gated cross-modal adapter that effectively combines visual and textual representations prior to input into a frozen LLM. This lightweight adapter, trained with minimal parameters, enables efficient cross-modal understanding. Notably, CROME demonstrates superior zero-shot performance on standard visual question answering and instruction-following benchmarks. Moreover, it yields fine-tuning with exceptional parameter efficiency, competing with task-specific specialist state-of-the-art methods. CROME demonstrates the potential of pre-LM alignment for building scalable, adaptable, and parameter-efficient multimodal models.

Multi-modal pretraining for learning high-level multi-modal representation is a further step towards deep learning and artificial intelligence. In this work, we propose a novel model, namely InterBERT (BERT for Interaction), which is the first model of our series of multimodal pretraining methods M6 (MultiModality-to-MultiModality Multitask Mega-transformer). The model owns strong capability of modeling interaction between the information flows of different modalities. The single-stream interaction module is capable of effectively processing information of multiple modalilties, and the two-stream module on top preserves the independence of each modality to avoid performance downgrade in single-modal tasks. We pretrain the model with three pretraining tasks, including masked segment modeling (MSM), masked region modeling (MRM) and image-text matching (ITM); and finetune the model on a series of vision-and-language downstream tasks. Experimental results demonstrate that InterBERT outperforms a series of strong baselines, including the most recent multi-modal pretraining methods, and the analysis shows that MSM and MRM are effective for pretraining and our method can achieve performances comparable to BERT in single-modal tasks. Besides, we propose a large-scale dataset for multi-modal pretraining in Chinese, and we develop the Chinese InterBERT which is the first Chinese multi-modal pretrained model. We pretrain the Chinese InterBERT on our proposed dataset of 3.1M image-text pairs from the mobile Taobao, the largest Chinese e-commerce platform. We finetune the model for text-based image retrieval, and recently we deployed the model online for topic-based recommendation.

Existing codecs are designed to eliminate intrinsic redundancies to create a compact representation for compression. However, strong external priors from Multimodal Large Language Models (MLLMs) have not been explicitly explored in video compression. Herein, we introduce a unified paradigm for Cross-Modality Video Coding (CMVC), which is a pioneering approach to explore multimodality representation and video generative models in video coding. Specifically, on the encoder side, we disentangle a video into spatial content and motion components, which are subsequently transformed into distinct modalities to achieve very compact representation by leveraging MLLMs. During decoding, previously encoded components and video generation models are leveraged to create multiple encoding-decoding modes that optimize video reconstruction quality for specific decoding requirements, including Text-Text-to-Video (TT2V) mode to ensure high-quality semantic information and Image-Text-to-Video (IT2V) mode to achieve superb perceptual consistency. In addition, we propose an efficient frame interpolation model for IT2V mode via Low-Rank Adaption (LoRA) tuning to guarantee perceptual quality, which allows the generated motion cues to behave smoothly. Experiments on benchmarks indicate that TT2V achieves effective semantic reconstruction, while IT2V exhibits competitive perceptual consistency. These results highlight potential directions for future research in video coding.

The emergence of large Vision Language Models (VLMs) has broadened the scope and capabilities of single-modal Large Language Models (LLMs) by integrating visual modalities, thereby unlocking transformative cross-modal applications in a variety of real-world scenarios. Despite their impressive performance, VLMs are prone to significant hallucinations, particularly in the form of cross-modal inconsistencies. Building on the success of Reinforcement Learning from Human Feedback (RLHF) in aligning LLMs, recent advancements have focused on applying direct preference optimization (DPO) on carefully curated datasets to mitigate these issues. Yet, such approaches typically introduce preference signals in a brute-force manner, neglecting the crucial role of visual information in the alignment process. In this paper, we introduce Re-Align, a novel alignment framework that leverages image retrieval to construct a dual-preference dataset, effectively incorporating both textual and visual preference signals. We further introduce rDPO, an extension of the standard direct preference optimization that incorporates an additional visual preference objective during fine-tuning. Our experimental results demonstrate that Re-Align not only mitigates hallucinations more effectively than previous methods but also yields significant performance gains in general visual question-answering (VQA) tasks. Moreover, we show that Re-Align maintains robustness and scalability across a wide range of VLM sizes and architectures. This work represents a significant step forward in aligning multimodal LLMs, paving the way for more reliable and effective cross-modal applications. We release all the code in https://github.com/taco-group/Re-Align.

Recent progress in 3D object generation has been fueled by the strong priors offered by diffusion models. However, existing models are tailored to specific tasks, accommodating only one modality at a time and necessitating retraining to change modalities. Given an image-to-3D model and a text prompt, a naive approach is to convert text prompts to images and then use the image-to-3D model for generation. This approach is both time-consuming and labor-intensive, resulting in unavoidable information loss during modality conversion. To address this, we introduce XBind, a unified framework for any-to-3D generation using cross-modal pre-alignment techniques. XBind integrates an multimodal-aligned encoder with pre-trained diffusion models to generate 3D objects from any modalities, including text, images, and audio. We subsequently present a novel loss function, termed Modality Similarity (MS) Loss, which aligns the embeddings of the modality prompts and the rendered images, facilitating improved alignment of the 3D objects with multiple modalities. Additionally, Hybrid Diffusion Supervision combined with a Three-Phase Optimization process improves the quality of the generated 3D objects. Extensive experiments showcase XBind's broad generation capabilities in any-to-3D scenarios. To our knowledge, this is the first method to generate 3D objects from any modality prompts. Project page: https://zeroooooooow1440.github.io/.

Audio visual segmentation (AVS) aims to segment the sounding objects for each frame of a given video. To distinguish the sounding objects from silent ones, both audio-visual semantic correspondence and temporal interaction are required. The previous method applies multi-frame cross-modal attention to conduct pixel-level interactions between audio features and visual features of multiple frames simultaneously, which is both redundant and implicit. In this paper, we propose an Audio-Queried Transformer architecture, AQFormer, where we define a set of object queries conditioned on audio information and associate each of them to particular sounding objects. Explicit object-level semantic correspondence between audio and visual modalities is established by gathering object information from visual features with predefined audio queries. Besides, an Audio-Bridged Temporal Interaction module is proposed to exchange sounding object-relevant information among multiple frames with the bridge of audio features. Extensive experiments are conducted on two AVS benchmarks to show that our method achieves state-of-the-art performances, especially 7.1% M_J and 7.6% M_F gains on the MS3 setting.

One critical challenge in 6D object pose estimation from a single RGBD image is efficient integration of two different modalities, i.e., color and depth. In this work, we tackle this problem by a novel Deep Fusion Transformer~(DFTr) block that can aggregate cross-modality features for improving pose estimation. Unlike existing fusion methods, the proposed DFTr can better model cross-modality semantic correlation by leveraging their semantic similarity, such that globally enhanced features from different modalities can be better integrated for improved information extraction. Moreover, to further improve robustness and efficiency, we introduce a novel weighted vector-wise voting algorithm that employs a non-iterative global optimization strategy for precise 3D keypoint localization while achieving near real-time inference. Extensive experiments show the effectiveness and strong generalization capability of our proposed 3D keypoint voting algorithm. Results on four widely used benchmarks also demonstrate that our method outperforms the state-of-the-art methods by large margins.

Visible-infrared person re-identification (VI-ReID) is a challenging task due to large cross-modality discrepancies and intra-class variations. Existing methods mainly focus on learning modality-shared representations by embedding different modalities into the same feature space. As a result, the learned feature emphasizes the common patterns across modalities while suppressing modality-specific and identity-aware information that is valuable for Re-ID. To address these issues, we propose a novel Modality Unifying Network (MUN) to explore a robust auxiliary modality for VI-ReID. First, the auxiliary modality is generated by combining the proposed cross-modality learner and intra-modality learner, which can dynamically model the modality-specific and modality-shared representations to alleviate both cross-modality and intra-modality variations. Second, by aligning identity centres across the three modalities, an identity alignment loss function is proposed to discover the discriminative feature representations. Third, a modality alignment loss is introduced to consistently reduce the distribution distance of visible and infrared images by modality prototype modeling. Extensive experiments on multiple public datasets demonstrate that the proposed method surpasses the current state-of-the-art methods by a significant margin.

With the increasing amount of multimedia data on modern mobile systems and IoT infrastructures, harnessing these rich multimodal data without breaching user privacy becomes a critical issue. Federated learning (FL) serves as a privacy-conscious alternative to centralized machine learning. However, existing FL methods extended to multimodal data all rely on model aggregation on single modality level, which restrains the server and clients to have identical model architecture for each modality. This limits the global model in terms of both model complexity and data capacity, not to mention task diversity. In this work, we propose Contrastive Representation Ensemble and Aggregation for Multimodal FL (CreamFL), a multimodal federated learning framework that enables training larger server models from clients with heterogeneous model architectures and data modalities, while only communicating knowledge on public dataset. To achieve better multimodal representation fusion, we design a global-local cross-modal ensemble strategy to aggregate client representations. To mitigate local model drift caused by two unprecedented heterogeneous factors stemming from multimodal discrepancy (modality gap and task gap), we further propose two inter-modal and intra-modal contrasts to regularize local training, which complements information of the absent modality for uni-modal clients and regularizes local clients to head towards global consensus. Thorough evaluations and ablation studies on image-text retrieval and visual question answering tasks showcase the superiority of CreamFL over state-of-the-art FL methods and its practical value.

Multi-modal Large Language Models (MLLMs) have recently exhibited impressive general-purpose capabilities by leveraging vision foundation models to encode the core concepts of images into representations. These are then combined with instructions and processed by the language model to generate high-quality responses. Despite significant progress in enhancing the language component, challenges persist in optimally fusing visual encodings within the language model for task-specific adaptability. Recent research has focused on improving this fusion through modality adaptation modules but at the cost of significantly increased model complexity and training data needs. In this paper, we propose EMMA (Efficient Multi-Modal Adaptation), a lightweight cross-modality module designed to efficiently fuse visual and textual encodings, generating instruction-aware visual representations for the language model. Our key contributions include: (1) an efficient early fusion mechanism that integrates vision and language representations with minimal added parameters (less than 0.2% increase in model size), (2) an in-depth interpretability analysis that sheds light on the internal mechanisms of the proposed method; (3) comprehensive experiments that demonstrate notable improvements on both specialized and general benchmarks for MLLMs. Empirical results show that EMMA boosts performance across multiple tasks by up to 9.3% while significantly improving robustness against hallucinations. Our code is available at https://github.com/SaraGhazanfari/EMMA

As the size of Large Multi-Modal Models (LMMs) increases consistently, the adaptation of these pre-trained models to specialized tasks has become a computationally and memory-intensive challenge. Traditional fine-tuning methods require isolated, exhaustive retuning for each new task, limiting the models' versatility. Moreover, current efficient adaptation techniques often overlook modality alignment, focusing only on the knowledge extraction of new tasks. To tackle these issues, we introduce Multiway-Adapter, an innovative framework incorporating an 'Alignment Enhancer' to deepen modality alignment, enabling high transferability without tuning pre-trained parameters. Our method adds fewer than 1.25\% of additional parameters to LMMs, exemplified by the BEiT-3 model in our study. This leads to superior zero-shot image-text retrieval performance compared to fully fine-tuned models, while achieving up to a 57\% reduction in fine-tuning time. Our approach offers a resource-efficient and effective adaptation pathway for LMMs, broadening their applicability. The source code is publicly available at: https://github.com/longkukuhi/MultiWay-Adapter.

Cross-modal retrieval aims to measure the content similarity between different types of data. The idea has been previously applied to visual, text, and speech data. In this paper, we present a novel cross-modal retrieval method specifically for multi-view images, called Cross-view Image Retrieval CVIR. Our approach aims to find a feature space as well as an embedding space in which samples from street-view images are compared directly to satellite-view images (and vice-versa). For this comparison, a novel deep metric learning based solution "DeepCVIR" has been proposed. Previous cross-view image datasets are deficient in that they (1) lack class information; (2) were originally collected for cross-view image geolocalization task with coupled images; (3) do not include any images from off-street locations. To train, compare, and evaluate the performance of cross-view image retrieval, we present a new 6 class cross-view image dataset termed as CrossViewRet which comprises of images including freeway, mountain, palace, river, ship, and stadium with 700 high-resolution dual-view images for each class. Results show that the proposed DeepCVIR outperforms conventional matching approaches on the CVIR task for the given dataset and would also serve as the baseline for future research.

This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision. Challenges in adapting Transformer from language to vision arise from differences between the two domains, such as large variations in the scale of visual entities and the high resolution of pixels in images compared to words in text. To address these differences, we propose a hierarchical Transformer whose representation is computed with Shifted windows. The shifted windowing scheme brings greater efficiency by limiting self-attention computation to non-overlapping local windows while also allowing for cross-window connection. This hierarchical architecture has the flexibility to model at various scales and has linear computational complexity with respect to image size. These qualities of Swin Transformer make it compatible with a broad range of vision tasks, including image classification (87.3 top-1 accuracy on ImageNet-1K) and dense prediction tasks such as object detection (58.7 box AP and 51.1 mask AP on COCO test-dev) and semantic segmentation (53.5 mIoU on ADE20K val). Its performance surpasses the previous state-of-the-art by a large margin of +2.7 box AP and +2.6 mask AP on COCO, and +3.2 mIoU on ADE20K, demonstrating the potential of Transformer-based models as vision backbones. The hierarchical design and the shifted window approach also prove beneficial for all-MLP architectures. The code and models are publicly available at~https://github.com/microsoft/Swin-Transformer.

We use (multi)modal deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies. We operationalize sites of multimodal integration as regions where a multimodal vision-language model predicts recordings better than unimodal language, unimodal vision, or linearly-integrated language-vision models. Our target DNN models span different architectures (e.g., convolutional networks and transformers) and multimodal training techniques (e.g., cross-attention and contrastive learning). As a key enabling step, we first demonstrate that trained vision and language models systematically outperform their randomly initialized counterparts in their ability to predict SEEG signals. We then compare unimodal and multimodal models against one another. Because our target DNN models often have different architectures, number of parameters, and training sets (possibly obscuring those differences attributable to integration), we carry out a controlled comparison of two models (SLIP and SimCLR), which keep all of these attributes the same aside from input modality. Using this approach, we identify a sizable number of neural sites (on average 141 out of 1090 total sites or 12.94%) and brain regions where multimodal integration seems to occur. Additionally, we find that among the variants of multimodal training techniques we assess, CLIP-style training is the best suited for downstream prediction of the neural activity in these sites.

Video-text retrieval is a class of cross-modal representation learning problems, where the goal is to select the video which corresponds to the text query between a given text query and a pool of candidate videos. The contrastive paradigm of vision-language pretraining has shown promising success with large-scale datasets and unified transformer architecture, and demonstrated the power of a joint latent space. Despite this, the intrinsic divergence between the visual domain and textual domain is still far from being eliminated, and projecting different modalities into a joint latent space might result in the distorting of the information inside the single modality. To overcome the above issue, we present a novel mechanism for learning the translation relationship from a source modality space S to a target modality space T without the need for a joint latent space, which bridges the gap between visual and textual domains. Furthermore, to keep cycle consistency between translations, we adopt a cycle loss involving both forward translations from S to the predicted target space T', and backward translations from T' back to S. Extensive experiments conducted on MSR-VTT, MSVD, and DiDeMo datasets demonstrate the superiority and effectiveness of our LaT approach compared with vanilla state-of-the-art methods.

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

A range of applications of multi-modal music information retrieval is centred around the problem of connecting large collections of sheet music (images) to corresponding audio recordings, that is, identifying pairs of audio and score excerpts that refer to the same musical content. One of the typical and most recent approaches to this task employs cross-modal deep learning architectures to learn joint embedding spaces that link the two distinct modalities - audio and sheet music images. While there has been steady improvement on this front over the past years, a number of open problems still prevent large-scale employment of this methodology. In this article we attempt to provide an insightful examination of the current developments on audio-sheet music retrieval via deep learning methods. We first identify a set of main challenges on the road towards robust and large-scale cross-modal music retrieval in real scenarios. We then highlight the steps we have taken so far to address some of these challenges, documenting step-by-step improvement along several dimensions. We conclude by analysing the remaining challenges and present ideas for solving these, in order to pave the way to a unified and robust methodology for cross-modal music retrieval.

Recent advances in multimodal vision and language modeling have predominantly focused on the English language, mostly due to the lack of multilingual multimodal datasets to steer modeling efforts. In this work, we address this gap and provide xGQA, a new multilingual evaluation benchmark for the visual question answering task. We extend the established English GQA dataset to 7 typologically diverse languages, enabling us to detect and explore crucial challenges in cross-lingual visual question answering. We further propose new adapter-based approaches to adapt multimodal transformer-based models to become multilingual, and -- vice versa -- multilingual models to become multimodal. Our proposed methods outperform current state-of-the-art multilingual multimodal models (e.g., M3P) in zero-shot cross-lingual settings, but the accuracy remains low across the board; a performance drop of around 38 accuracy points in target languages showcases the difficulty of zero-shot cross-lingual transfer for this task. Our results suggest that simple cross-lingual transfer of multimodal models yields latent multilingual multimodal misalignment, calling for more sophisticated methods for vision and multilingual language modeling.