Learning the Task or Learning the Verifier? Rethinking Criteria Exposure in Embodied Self-Improvement Paper • 2611.08318 • Published 15 days ago • 22
Enhancing Spatial Understanding in Image Generation via Reward Modeling Paper • 2602.24233 • Published Feb 27 • 56
MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head Paper • 2601.07832 • Published Jan 12 • 53
Universal Humanoid 1.0 Collection Official dataset and models for the paper "Learning from Massive Human Videos for Universal Humanoid Pose Control" • 3 items • Updated 9 days ago • 2