Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 4 days ago • 226
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 9 days ago • 347
HDP: A Lightweight Cryptographic Protocol for Human Delegation Provenance in Agentic AI Systems Paper • 2604.04522 • Published 6 days ago • 8
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published 16 days ago • 153