Shaowei Liu
I'm a Research Scientist in NVIDIA's Fundamental Generative AI Research (GenAIR) group led by Arash Vahdat. I received my Ph.D. in Computer Science from the University of Illinois Urbana-Champaign, advised by Prof. Shenlong Wang and Prof. Saurabh Gupta.
Prior to that, I received my M.S. in Computer Science from UC San Diego, advised by Prof. Xiaolong Wang, and my B.S. in Electronic Engineering from Tsinghua University. My research focuses on generative modeling.
|
|
|
Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video
Generation
Siyi Chen, Shaowei Liu, Yixuan Jia, Zian Wang, Huan Ling, Qing Qu, Jun Gao Preprint, 2026. Paper Project Code TL;DR
A one-line modification to the DMD loss introduces real-data supervision.
|
|
|
|
MoRE: Mixture-of-Experts for Multi-Physics Robotic World Models
Ziyu Zhu*, Shaowei Liu*, Albert J. Zhai*, Henry Che, Wei-Chiu Ma, Shenlong Wang Conference on Robot Learning (CoRL), 2026. Spotlight Paper Project Code TL;DR
3D world model with Mixture of motion experts for multi-physics robotic
manipulation.
|
|
MoRight: Motion Control Done Right
Shaowei Liu, Xuanchi Ren, Tianchang Shen, Huan Ling, Saurabh Gupta, Shenlong Wang, Sanja Fidler, Jun Gao European Conference on Computer Vision (ECCV), 2026. Paper Project TL;DR
Controllable video generation with disentangled camera-object motion control and
causal motion reasoning.
|
|
VisualSync: Multi-Camera Synchronization via Cross-View Object Motion
Shaowei Liu*, David Yifan Yao*, Saurabh Gupta†, Shenlong Wang† Conference on Neural Information Processing Systems (NeurIPS), 2025. Paper Project Code TL;DR
Align unsynchronized multi-view videos by matching object motion with epipolar
cues.
|
|
Ponimator: Unfolding Interactive Pose for Versatile Human-Human Interaction
Animation
Shaowei Liu, Chuan Guo*, Bing Zhou*, Jian Wang* International Conference on Computer Vision (ICCV), 2025. Paper Project Code TL;DR
Interaction human-human motion animation and generation anchored on interactive
poses.
|
|
PhysGen3D: Crafting a Miniature Interactive World from a Single Image
Boyuan Chen, Hanxiao Jiang, Shaowei Liu, Saurabh Gupta, Yunzhu Li, Hao Zhao, Shenlong Wang Conference on Computer Vision and Pattern Recognition (CVPR), 2025. Paper Project Code TL;DR
Synthesizes video of a miniature interactive world from a single image.
|
|
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
Shaowei Liu, Zhongzheng Ren, Saurabh Gupta*, Shenlong Wang* European Conference on Computer Vision (ECCV), 2024. Paper Project Code TL;DR
Image-to-video generation pipeline integrates physical simulation and video
diffusion prior.
|
|
ContactGen: Generative Contact Modeling for Grasp Generation
Shaowei Liu, Yang Zhou, Jimei Yang, Saurabh Gupta*, Shenlong Wang* International Conference on Computer Vision (ICCV), 2023. Paper Project Code TL;DR
A novel object-centric contact representation for hand-object interaction.
|
|
Building Rearticulable Models for Arbitrary 3D Objects from 4D Point Clouds
Shaowei Liu, Saurabh Gupta*, Shenlong Wang* Conference on Computer Vision and Pattern Recognition (CVPR), 2023. Paper Project Code TL;DR
Build animatable 3D models from arbitrary articulated object point cloud
sequence.
|
|
CASA: Category-agnostic Skeletal Animal Reconstruction
Yuefan Wu*, Zeyuan Chen*, Shaowei Liu, Zhongzheng Ren, Shenlong Wang Conference on Neural Information Processing Systems (NeurIPS), 2022. Paper Project Code TL;DR
Category-agnostic 3D animal reconstruction from a monocular video.
|
|
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Yuzhe Qin*, Yueh-Hua Wu*, Shaowei Liu, Hanwen Jiang, Ruihan Yang, Yang Fu, European Conference on Computer Vision (ECCV), 2022. Paper Project Code TL;DR
A new platform and pipeline for dexterous manipulation from videos.
|
|
Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos
Shaowei Liu, Subarna Tripathi, Somdeb Majumdar, Xiaolong Wang Conference on Computer Vision and Pattern Recognition (CVPR), 2022. Paper Project Code TL;DR
Forecast future hand-object interactions given an egocentric video.
|
|
Hand-Object Contact Consistency Reasoning for Human Grasps Generation
Hanwen Jiang*, Shaowei Liu*, Jiashun Wang and Xiaolong Wang International Conference on Computer Vision (ICCV), 2021. Oral Paper Project Code TL;DR
Generate natural human grasps given a 3D object in the world.
|
|
Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time
Shaowei Liu*, Hanwen Jiang*, Jiarui Xu, Sifei Liu and Xiaolong Wang Conference on Computer Vision and Pattern Recognition (CVPR), 2021. Paper Project Code TL;DR
Build a joint learning framework for estimating the 3D hand and object poses.
|
|
Light and Fast Hand Pose Estimation From Spatial-Decomposed Latent Heatmap
Shaowei Liu, Guijin Wang, Pengwei Xie, Cairong Zhang IEEE Access, 2020. Paper BibTeX TL;DR
A light and efficient approach for depth-based hand pose estimation.
|
|
|
