Boyi Li

Vision-language-action models can achieve superior performance and drastically reduced latency by leveraging reasoning supervision without explicitly conditioning actions on generated reasoning.

Robots can't truly improve themselves yet; current systems lack the crucial ability to recursively refine their own learning processes based on physical experience.

Embodied AI agents can now continuously self-improve by co-evolving their policies, training curricula, and judges, overcoming the bottleneck of static evaluation.

Language, when self-evolving and treated as a physical representation, can unlock state-of-the-art physical plausibility in video world models, even surpassing proprietary systems.