I am a PhD candidate at Purdue University. My PhD advisor is Daniel Aliaga . I am interested in integrating advanced techniques to broad interdisciplinary CV/CG problems. My research focuses on generation, reconstruction, and representation learning of 2D/3D layouts and scenes. I am currently working on multi-modal LLMs (MLLM) for physical-based video generation, and leveraging synthetic data generation for MLLM benchmark and evaluation.
Email / CV / GitHub / Google Scholar / LinkedIn
Kubrick: Multimodal Agent Collaborations for Video Generation Liu He , Yizhi Song, Hejun Huang, Xin Zhou Paper Drafting > proj > paper (Coming Soon)