Xingang Pan

ClothTransformer achieves state-of-the-art cloth simulation by learning a unified latent space, allowing a single model to handle diverse scenarios and mesh resolutions with significantly improved accuracy and collision handling.

Text-to-image flow models can achieve superior preference alignment by augmenting the condition space, creating a "dense" reward mapping that better captures inter-sample relationships.

Unlock real-time 4D scene understanding from monocular video with a novel "encode-once, query-anywhere and anytime" framework that jointly models geometry and motion.