Weiwei Wu

Evolving video agents can boost long-form video understanding accuracy by over 13 percentage points while dramatically reducing processing costs.

IViT achieves 93.80% accuracy in skin disease detection while reducing feature redundancy by 29.5%, striking a crucial balance between interpretability and performance.

Quadruped robots can walk nearly three times longer with heavy payloads by learning a thermal-aware policy on top of a standard locomotion controller.