GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 7 days ago • 107
DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models Paper • 2603.26164 • Published 13 days ago • 325
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms Paper • 2603.28489 • Published 10 days ago • 30
InCoder-32B: Code Foundation Model for Industrial Scenarios Paper • 2603.16790 • Published 23 days ago • 307
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published Mar 4 • 210