new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Apr 2

Submitted by

akhaliq

Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order

·
45 authors

Submitted by

akhaliq

Getting it Right: Improving Spatial Consistency in Text-to-Image Models

·
11 authors

Submitted by

akhaliq

FlexiDreamer: Single Image-to-3D Generation with FlexiCubes

·
5 authors

Submitted by

akhaliq

MaGRITTe: Manipulative and Generative 3D Realization from Image, Topview and Text

·
2 authors

Submitted by

akhaliq

Measuring Style Similarity in Diffusion Models

·
8 authors

Submitted by

akhaliq

CosmicMan: A Text-to-Image Foundation Model for Humans

·
6 authors

Submitted by

akhaliq

Streaming Dense Video Captioning

·
8 authors

Submitted by

akhaliq

Condition-Aware Neural Network for Controlled Image Generation

·
6 authors

Submitted by

akhaliq

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward

·
11 authors

Submitted by

akhaliq

WavLLM: Towards Robust and Adaptive Speech Large Language Model

·
11 authors

Submitted by

akhaliq

Noise-Aware Training of Layout-Aware Language Models

·
8 authors

Submitted by

akhaliq

ST-LLM: Large Language Models Are Effective Temporal Learners

·
6 authors