Chenhao Zhang

Explicitly linking multimodal patient data to biomedical knowledge graphs unlocks significant gains for clinical LLMs, with performance plummeting when these crucial connections are removed.

Video generative priors only translate into robust physical control when paired with explicit world-to-action information routing and synchronized joint denoising rather than standard monolithic fine-tuning.

Scheduling imagination in VLA models can cut GPU costs by 80% while boosting performance and robustness in real-world tasks.

Current autonomous AI agents are alarmingly unprepared for real-world adversarial attacks, often missing critical vulnerabilities in dynamic environments.

OneVLA unifies navigation and manipulation tasks into a single framework, enabling robots to seamlessly interpret commands and interact with their environments like never before.