GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published 5 days ago • 51
GEMS: Agent-Native Multimodal Generation with Memory and Skills Paper • 2603.28088 • Published 8 days ago • 83
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published 22 days ago • 152
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151