Yuxiang Zhang

Human-as-Humanoid achieves a staggering 4.8–7.2x increase in demonstration throughput, transforming how humanoid robots learn from human actions.

BiPACE transforms credit assignment in LLM training, boosting validation success rates by over 6% without the need for critics or extra rollouts.

Structured allocentric representations can boost spatial reasoning in foundation models by up to 18%, even in the absence of visual inputs.