OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models Paper • 2604.10866 • Published 4 days ago • 45
SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments Paper • 2604.14144 • Published 1 day ago • 57
RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 4 days ago • 84
Seedance 2.0: Advancing Video Generation for World Complexity Paper • 2604.14148 • Published 1 day ago • 92
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning Paper • 2602.21420 • Published Feb 24 • 6