Denser neq Better: Limits of On-Policy Self-Distillation for Continual Post-Training Paper • 2607.01763 • Published 2 days ago • 4
FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search Paper • 2606.00660 • Published May 30 • 8
PhysX-Omni: Unified Simulation-Ready Physical 3D Generation for Rigid, Deformable, and Articulated Objects Paper • 2605.21572 • Published May 20 • 55
MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping Paper • 2604.08364 • Published Apr 9 • 103
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published Mar 17 • 248