Mean Mode Screaming: Mean--Variance Split Residuals for 1000-Layer Diffusion Transformers Paper • 2605.06169 • Published 8 days ago • 148
SEIF: Self-Evolving Reinforcement Learning for Instruction Following Paper • 2605.07465 • Published 7 days ago • 26
HERMES++: Toward a Unified Driving World Model for 3D Scene Understanding and Generation Paper • 2604.28196 • Published 15 days ago • 71
The Last Human-Written Paper: Agent-Native Research Artifacts Paper • 2604.24658 • Published 16 days ago • 20
Cog-DRIFT: Exploration on Adaptively Reformulated Instances Enables Learning from Hard Reasoning Problems Paper • 2604.04767 • Published Apr 6 • 7
GrandCode: Achieving Grandmaster Level in Competitive Programming via Agentic Reinforcement Learning Paper • 2604.02721 • Published Apr 3 • 628
PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models Paper • 2603.28763 • Published Mar 30 • 7
AVControl: Efficient Framework for Training Audio-Visual Controls Paper • 2603.24793 • Published Mar 25 • 28
HSImul3R: Physics-in-the-Loop Reconstruction of Simulation-Ready Human-Scene Interactions Paper • 2603.15612 • Published Mar 16 • 153
Bootstrapping Exploration with Group-Level Natural Language Feedback in Reinforcement Learning Paper • 2603.04597 • Published Mar 4 • 210
Does Your Reasoning Model Implicitly Know When to Stop Thinking? Paper • 2602.08354 • Published Feb 9 • 264