TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation Paper • 2605.22355 • Published 1 day ago • 56
Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos Paper • 2605.18233 • Published 4 days ago • 83
MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation Paper • 2512.18181 • Published 15 days ago • 85
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation Paper • 2604.18168 • Published Apr 20 • 97
Elucidating the SNR-t Bias of Diffusion Probabilistic Models Paper • 2604.16044 • Published Apr 17 • 74
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver Paper • 2604.08377 • Published Apr 9 • 291
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models Paper • 2603.22212 • Published Mar 23 • 126
Video-CoE: Reinforcing Video Event Prediction via Chain of Events Paper • 2603.14935 • Published Mar 16 • 91
Geometry-Guided Reinforcement Learning for Multi-view Consistent 3D Scene Editing Paper • 2603.03143 • Published Mar 3 • 145