PhysBrain: Human Egocentric Data as a Bridge from Vision Language Models to Physical Intelligence Paper • 2512.16793 • Published 10 days ago • 71
TrajSelector: Harnessing Latent Representations for Efficient and Effective Best-of-N in Large Reasoning Model Paper • 2510.16449 • Published Oct 18 • 34
Euclid's Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks Paper • 2509.24473 • Published Sep 29 • 17