I am a researcher at Rhoda AI, working on robot foundation models. Previously, I was a Research Scientist at NVIDIA Research, Cosmos Lab, where I was a founding member of Cosmos World Foundation Model and a core contributor across Cosmos 1, 2, and 3. 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 robot foundation models, world models, and generative 3D/4D perception for Physical AI.

Selected Publications

• Cosmos 3: Omnimodal World Models for Physical AI
  arXiv 2026
  NVIDIA
  Project PDF Code Models
• Cosmos-Predict2.5: Improved World Simulation with Video Foundation Models for Physical AI
  arXiv 2025
  NVIDIA
  Project PDF Code
• Cosmos World Foundation Model Platform for Physical AI
  arXiv 2025
  NVIDIA
  Project PDF Code
• MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single to Sparse-view 3D Object Reconstruction
  ECCV 2024
  Shitao Tang*, Jiacheng Chen*, Dilin Wang*, Chengzhou Tang, Fuyang Zhang, Yuchen Fan, Vikas Chandra, Rakesh Ranjan, Yasutaka Furukawa
  Project PDF
• MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
  NeurIPS 2023 Spotlight
  Shitao Tang*, Fuyang Zhang*, Jiacheng Chen, Peng Wang, Yasutaka Furukawa
  Project Demo PDF Code
• NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization
  CVPR 2023
  Shitao Tang, Sicong Tang, Andrea Tagliasacchi, Ping Tan, Yasutaka Furukawa
  PDF Code
• QuadTree Attention for Vision Transformers
  ICLR 2022
  Shitao Tang*, Jiahui Zhang*, Siyu Zhu, Ping Tan
  PDF Code

→ Full publication list