research

Currently, I'm collaborating with with Yining Hong and Andrew Lizarraga on applying vision-language models to collaborative embodied agents. Over the summer, I worked on datasets for action-driven video generation as well as memory-augmented video generation for our project.

Previously, I worked on on applying physics to meshes created by Gaussian Splatting methods with the Visual Machines Group led by Professor Achuta Kadambi.

publications

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation
Yining Hong; Beide Liu*; Maxine Wu*; Yuanhao Zhai; Kai-Wei Chang; Lingjie Li; Kevin Lin; Chung-Ching Lin; Jianfeng Wang; Zhengyuan Yang††; Yingnian Wu††; Lijuan Wang††
ICLR 2025 [Project Page] [Paper]