Yong Dai

A single visual interface, action views, bridges the gap between video generation models and diverse robotic embodiments, enabling unified action modeling and execution.

Qualitative generalization across trajectory, scene, object, embodiment, and viewpoint shifts highlights Pelican-Sim's potential as a general-purpose world model simulator.

Achieving state-of-the-art performance with a surprisingly simple architecture, OPUS shows that complexity in open-vocabulary detection isn't always necessary.

Routing previously encoded evidence in HR-VQA can yield up to 9.9-point improvements on benchmarks while slashing inference time by over 97%.