Chao Liu

Research Scientist, NVIDIA Research
chaoliu@nvidia.com

About

I am a Research Scientist at NVIDIA Research, where I work on generative models and 3D vision. My research spans video generation, fast generative sampling, controllable and 3D-consistent generation, and physics-based computational imaging. I received my Ph.D. in Robotics from Carnegie Mellon University, advised by Srinivasa G. Narasimhan and Artur W. Dubrawski.

Research Interests

Video generation and world models: long-horizon, autoregressive, and bidirectional video diffusion, and temporally consistent noise for equivariant video models, as a foundation for simulating the physical world.
Fast generative sampling: distillation methods that bring diffusion and flow models down to a few network evaluations without losing diversity.
Controllable and compositional generation: structured representations such as blobs and camera poses that give users precise control over images, videos, and 3D scenes.
3D vision and generation: 3D-consistent synthesis, point cloud generation, and real-time 3D portrait reconstruction for telepresence.
Computational imaging and physics-based vision: recovering depth, shape, thin structures, and subsurface tissue from compact camera and lighting setups such as focal stacks, near-light photometric stereo, and diffuse optical tomography, as well as diffusion-based MRI reconstruction.

Publications

Parallel Decoding Distillation for Fast Image and Video Generation Neta Shaul, Chao Liu, Arash Vahdat, Julius Berner arXiv 2026 arXiv Project
DLSS 5: Real-Time Generative Rendering NVIDIA Technical Report, 2026 PDF Project
Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model Xinyin Ma, Julius Berner, Chao Liu, Arash Vahdat, Weili Nie, Xinchao Wang ICML 2026, Spotlight arXiv Project
Mode Seeking meets Mean Seeking for Fast Long Video Generation Shengqu Cai, Weili Nie^*, Chao Liu^*, Julius Berner, Lvmin Zhang, Nanye Ma, Hansheng Chen, Maneesh Agrawala, Leonidas Guibas, Gordon Wetzstein, Arash Vahdat ICML 2026 arXiv Project
Transition Matching Distillation for Fast Video Generation Weili Nie, Julius Berner, Nanye Ma, Chao Liu, Saining Xie, Arash Vahdat CVPR 2026 arXiv Project
EquiVDM: Equivariant Video Diffusion Models with Temporally Consistent Noise Chao Liu, Arash Vahdat arXiv 2025 arXiv Project
BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations Weixi Feng, Chao Liu, Sifei Liu, William Yang Wang, Arash Vahdat, Weili Nie CVPR 2025 PDF arXiv Project
Coherent 3D Portrait Video Reconstruction via Triplane Fusion Shengze Wang, Xueting Li, Chao Liu, Matthew Chan, Michael Stengel, Henry Fuchs, Shalini De Mello, Koki Nagano CVPR 2025 arXiv Project
Not-So-Optimal Transport Flows for 3D Point Cloud Generation Ka-Hei Hui, Chao Liu, Xiaohui Zeng, Chi-Wing Fu, Arash Vahdat ICLR 2025 arXiv Project
BlobGEN-3D: Compositional 3D-Consistent Freeview Image Generation with 3D Blobs Chao Liu, Weili Nie, Sifei Liu, Abhishek Badki, Hang Su, Morteza Mardani, Benjamin Eckart, Arash Vahdat SIGGRAPH Asia 2024 ACM PDF
Compositional Text-to-Image Generation with Dense Blob Representations Weili Nie, Sifei Liu, Morteza Mardani, Chao Liu, Benjamin Eckart, Arash Vahdat ICML 2024 arXiv Project
Learning to Jointly Understand Visual and Tactile Signals Yichen Li, Yilun Du, Chao Liu, Chao Liu, Francis Williams, Michael Foshey, Benjamin Eckart, Jan Kautz, Joshua B. Tenenbaum, Antonio Torralba, Wojciech Matusik ICLR 2024 PDF
CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation Dejia Xu, Weili Nie, Chao Liu, Sifei Liu, Jan Kautz, Zhangyang Wang, Arash Vahdat arXiv 2024 arXiv Project
Live 3D Portrait: Real-Time Radiance Fields for Single-Image Portrait View Synthesis Alex Trevithick, Matthew Chan, Michael Stengel, Eric R. Chan, Chao Liu, Zhiding Yu, Sameh Khamis, Manmohan Chandraker, Ravi Ramamoorthi, Koki Nagano SIGGRAPH 2023 (ACM TOG) arXiv Project
AI-Mediated 3D Video Conferencing Michael Stengel, Koki Nagano, Chao Liu, Matthew Chan, Alex Trevithick, Shalini De Mello, Jonghyun Kim, David Luebke SIGGRAPH 2023 Emerging Technologies ACM Project
SMRD: SURE-based Robust MRI Reconstruction with Diffusion Models Batu Ozturkler, Chao Liu, Benjamin Eckart, Morteza Mardani, Jiaming Song, Jan Kautz MICCAI 2023 arXiv Springer Code
Online Overexposed Pixels Hallucination in Videos with Adaptive Reference Frame Selection Yazhou Xing, Amrita Mazumdar, Anjul Patney, Chao Liu, Hongxu Yin, Qifeng Chen, Jan Kautz, Iuri Frosio arXiv 2023 arXiv
High Resolution Diffuse Optical Tomography using Short Range Indirect Subsurface Imaging Chao Liu, Akash K. Maity, Artur W. Dubrawski, Ashutosh Sabharwal, Srinivasa G. Narasimhan ICCP 2020, Best Paper Honorable Mention PDF Project
Neural RGB→D Sensing: Depth and Uncertainty from a Video Camera Chao Liu, Jinwei Gu, Kihwan Kim, Srinivasa G. Narasimhan, Jan Kautz CVPR 2019, Best Paper Finalist PDF arXiv Project Code
Near-Light Photometric Stereo using Circularly Placed Point Light Sources Chao Liu, Srinivasa G. Narasimhan, Artur W. Dubrawski ICCP 2018 Project
Matting and Depth Recovery of Thin Structures using a Focal Stack Chao Liu, Srinivasa G. Narasimhan, Artur W. Dubrawski CVPR 2017 PDF Project