On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics Paper • 2609.35259 • Published 29 days ago • 206
Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing Paper • 2610.00825 • Published 27 days ago • 22
PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop Paper • 2610.00559 • Published 27 days ago • 69
Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces Paper • 2609.40362 • Published 27 days ago • 40
nisten/opus5-5-doctor-patient-conversations-all-human-diseases Preview • Updated 30 days ago • 5.37k • 340