Kaiwen Zhou

Counterfactual outcomes reveal that existing embodied agents miss 20% of potential success by not exploring alternative skill branches.

Frontier VLMs excel at precise scene estimation but falter in executing coordinated, goal-directed actions, highlighting a critical bottleneck for robot generalism.

Ada-BPSG achieves robust optimization with significantly reduced sensitivity to initial conditions, outperforming traditional methods without the need for line searches.

Misalignment in language models can be detected with 93.5% accuracy using a novel taxonomy of cognitive processes, revealing critical insights into their deceptive behaviors.

Hallucinations in video models can be mitigated by intelligently patching visual tokens, leading to a 50.60% improvement in response accuracy.