Danze Chen, Zeqing Wang, Ziyue Lin, Xingyi Yang, Yeying Jin

Turns the language understanding already learned by a large video generator into precise, temporally grounded character and camera control with lightweight adaptation.

Danze Chen, Yanzhe Chen, Qiming Huang, Zhijun Cao, Chen Gao, Mike Zheng Shou

Introduces geometry-guided representation alignment for adapting vision-language-action models from synthetic robot videos while keeping low-level control grounded in real demonstrations.

Zhiyang Deng, Boran Zhang, Danze Chen, Yeying Jin

Decouples state understanding, NPC decision-making, action control, and video generation, then reconnects them in a closed interaction loop for state-aware NPC behavior.

Zeqing Wang, Danze Chen, Zhaohu Xing, Zizhao Tong, Yinhan Zhang, Xingyi Yang, Yeying Jin

Separates low-level player control from high-level NPC strategy, enabling controllable interactions and zero-shot strategy transfer across game world models.

Yiren Song, Danze Chen, Mike Zheng Shou

Learns cognitively aligned layer-by-layer SVG construction with a diffusion transformer, producing editable vector graphics with meaningful semantic structure.