I am a Research Scientist at NVIDIA Research, Deep Imagination Group. I received my Ph.D. from Simon Fraser University, supervised by Prof. Yasutaka Furukawa, and my M.S. under the supervision of Prof. Ping Tan.
My research focuses on world models and generative 3D/4D perception for Physical AI.
Selected Publications
- Cosmos World Foundation Model Platform for Physical AI
- MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single to Sparse-view 3D Object Reconstruction
- MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
- NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
- QuadTree Attention for Vision Transformers
