new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Mar 17

Submitted by

jianhongbai

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video

·
11 authors

4

Submitted by

kwanyoung

PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity

·
2 authors

1

Submitted by

SiyuanH

Adversarial Data Collection: Human-Collaborative Perturbations for Efficient and Robust Robotic Imitation Learning

·
8 authors

1

Submitted by

Messi-Hua

Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models

·
11 authors

1

Submitted by

vyokky

API Agents vs. GUI Agents: Divergence and Convergence

·
7 authors

1

Submitted by

gpx333

Exploring the Vulnerabilities of Federated Learning: A Deep Dive into Gradient Inversion Attacks

·
10 authors

1

Submitted by

ekazakos

Large-scale Pre-training for Grounded Video Caption Generation

·
3 authors

1

Submitted by

turkeyju

FlowTok: Flowing Seamlessly Across Text and Image Tokens

·
4 authors

1

Submitted by

akhaliq

TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools

·
8 authors

2

Submitted by

maitysubhajit

Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?

·
4 authors

1

Submitted by

JianyuanWang

VGGT: Visual Geometry Grounded Transformer

·
6 authors

1

Submitted by

Fr0zencr4nE

Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption

·
5 authors

1

Submitted by

yefly

Neighboring Autoregressive Modeling for Efficient Visual Generation

·
7 authors

2

Submitted by

kpzhang996

ProJudge: A Multi-Modal Multi-Discipline Benchmark and Instruction-Tuning Dataset for MLLM-based Process Judges

·
11 authors

1

Submitted by

kpzhang996

ARMOR v0.1: Empowering Autoregressive Multimodal Understanding Model with Interleaved Multimodal Generation via Asymmetric Synergy

·
10 authors

1

Submitted by

Luo-Yihong

Learning Few-Step Diffusion Models by Trajectory Distribution Matching

·
5 authors

2

Submitted by

nielsr

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

·
6 authors

Submitted by

andito

SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion

·
13 authors

1

Submitted by

Boqian-Li

ETCH: Generalizing Body Fitting to Clothed Humans via Equivariant Tightness

·
5 authors

1

Submitted by

zhwang4ai

Open-World Skill Discovery from Unsegmented Demonstrations

·
5 authors

2

Submitted by

WonderingWorld

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

·
8 authors

1

Submitted by

slionar

TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing

·
3 authors

1

Submitted by

mihoesche

Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?

·
5 authors

1

Submitted by

yangzhifei

MaRI: Material Retrieval Integration across Domains

·
6 authors

1

Submitted by

bpop

From TOWER to SPIRE: Adding the Speech Modality to a Text-Only LLM

·
8 authors

1

Submitted by

tdemin16

Group-robust Machine Unlearning

·
5 authors

1