Yangguang Li

I am a Senior Consultant at Shanghai AI Lab from 2021.

I am a Research Director at VAST from 2023.04 to 2025.04.

Before that I was a Research Leader at SenseTime.

I am focusing on world model and 3D generation research.

I am PhD from the Chinese University of Hong Kong.

Email  /  Google Scholar

• 2026.05: Recent oral/highlight/spotlight papers: SparseFlex (Oral, ICCV 2025), Faithful Contouring (Oral, CVPR 2026), Transition Models (Highlight, CVPR 2026), SceneTransporter (Spotlight, ICML 2026).
• 2026.04: Matrix-Game 2.0 and Matrix-Game 3.0 are released, pioneering open-source real-time interactive world modeling and advancing long-horizon memory for stable world simulation.
• 2026.01: UniPic 2.0 and UniPic 3.0 are released, a cost-efficient unified VLM+Diffusion framework for image understanding and editing, from GRPO-based editing to multi-image fusion at SOTA performance.
• 2025.05: I serve as a speaker at ICCV 2025 tutorial about 3D generation foundation models: 3DGenTutorial.
• 2025.04: I serve as an Area Chair for NeurIPS 2025.
• 2025.03: We release TripoSF, which was the best image-to-3D generation model.
• 2025.02: We release TripoSG, which was the best image-to-3D generation model at the time.
• 2024.12: Our paper TexGen won the Best Paper Honorable Mention Award in Siggraph Asia 2024.
• 2024.03: We release TripoSR with Stability AI, which was the fastest image-to-3D reconstruction model at the time.
• 2023.12: We launches 3D generation product TripoAI.

• Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
  Zile Wang, Zexiang Liu, Jiaxing Li, Kaichen Huang, Baixin Xu, Fei Kang, Mengyin An, Peiyu Wang, Biao Jiang, Yichen Wei, Yidan Xietian, Jiangbo Pei, Liang Hu, Boyi Jiang, Hua Xue, Zidong Wang, Haofeng Sun, Wei Li, Wanli Ouyang, Xianglong He, Yangguang Li, Yahui Zhou
  [Paper][Code][Arxiv 2026.4]
• Matrix-Game 2.0: An Open-Source, Real-Time, and Streaming Interactive World Model
  Xianglong He, Chunli Peng, Zexiang Liu, Boyang Wang, Yifan Zhang, Qi Cui, Fei Kang, Biao Jiang, Mengyin An, Yangyang Ren, Baixin Xu, Hao-Xiang Guo, Kaixiong Gong, Size Wu, Wei Li, Xuchen Song, Yang Liu, Yangguang Li, Yahui Zhou
  [Paper][Code][Arxiv 2025.8]
• Matrix-Game: Interactive World Foundation Model
  Yifan Zhang, Chunli Peng, Boyang Wang, Puyi Wang, Qingcheng Zhu, Fei Kang, Biao Jiang, Zedong Gao, Eric Yangguang Li, Yang Liu, Yahui Zhou
  [Paper][Code][Arxiv 2025.6]
• Matrix-3D: Omnidirectional Explorable 3D World Generation
  Zhongqi Yang, Wenhang Ge, Yuqi Li, Jiaqi Chen, Haoyuan Li, Mengyin An, Fei Kang, Hua Xue, Baixin Xu, Yuyang Yin, Eric Yangguang Li, Yang Liu, Yikai Wang, Hao-Xiang Guo, Yahui Zhou
  [Paper][Code][Arxiv 2025.8]
• Skywork UniPic 3.0: Unified Multi-Image Composition via Sequence Modeling
  Hongyang Wei, Hongbo Liu, Zidong Wang, Yi Peng, Baixin Xu, Size Wu, Xuying Zhang, Xianglong He, Zexiang Liu, Peiyu Wang, Xuchen Song, Yangguang Li, Yang Liu, Yahui Zhou
  [Paper][Code][Arxiv 2026.1]
• Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model
  Hongyang Wei, Baixin Xu, Hongbo Liu, Size Wu, Jie Liu, Yi Peng, Peiyu Wang, Zexiang Liu, Jingwen He, Yidan Xietian, Chuanxin Tang, Zidong Wang, Yichen Wei, Liang Hu, Boyi Jiang, Wei Li, Ying He, Yang Liu, Xuchen Song, Yangguang Li, Yahui Zhou
  [Paper][Code][Arxiv 2025.9]
• TripoSR: Fast 3D Object Reconstruction from a Single Image
  Dmitry Tochilkin, David Pankratz, Zexiang Liu, Zixuan Huang, Adam Letts, Yangguang Li, Ding Liang, Christian Laforte, Varun Jampani, Yan-Pei Cao
  [Paper][Code][Arxiv 2024.3]
• From Geometry to Texture: A Hierarchical Framework for Efficient Text-to-3D Generation
  Yangguang Li, Zehuan Huang, Feng Liang, Bin Huang, Qinghong Sun, Xihui Liu, Lu Sheng, Wanli Ouyang, Jing Shao
  [Paper][Demo][Technical Report 2023.4]

• PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion
  Yuyang Yin, Hao-Xiang Guo, Fangfu Liu, Mengyu Wang, Hanwen Liang, Eric Yangguang Li, Yikai Wang, Xiaojie Jin, Yao Zhao, Yunchao Wei
  [Paper][ICML 2026 Spotlight]
• Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface
  Yihao Luo, Xianglong He, Chuanyu Pan, Yiwen Chen, Jiaqi Wu, Yangguang Li, Wanli Ouyang, Yuanming Hu, Guang Yang, ChoonHwai Yap
  [Paper][Code][CVPR 2026 Oral]
• Transition Models: Rethinking the Generative Learning Objective
  Zidong Wang, Yiyuan Zhang, Xiaoyu Yue, Xiangyu Yue, Yangguang Li, Wanli Ouyang, Lei Bai
  [Paper][Code][CVPR 2026 Highlight]
• DynamicsBoost: Dynamic Plausible Video Generation via Annotation-Free Continuation Preference Optimization
  Jiaxing Li, Jiepeng Wang, Junyao Gao, Yang Liu, Eric Yangguang Li, Bo An, Hao-Xiang Guo
  [Paper][Code][CVPR 2026]
• HoloPart: Generative 3D Part Amodal Segmentation
  Yunhan Yang, Yuan-Chen Guo, Yukun Huang, Zi-Xin Zou, Zhipeng Yu, Yangguang Li, Yan-Pei Cao, Xihui Liu
  [Paper][Code][ICLR 2026]
• SceneTransporter: Optimal Transport-Guided Compositional Latent Diffusion for Single-Image Structured 3D Scene Generation
  Ling Wang, Hao-Xiang Guo, Xinzhou Wang, Fuchun Sun, Kai Sun, Pengkun Liu, Hang Xiao, Zhong Wang, Guangyuan Fu, Eric Yangguang Li, Yang Liu, Yikai Wang
  [Paper][ICLR 2026]
• Flow-GRPO: Training Flow Matching Models via Online RL
  Jie Liu, Gongye Liu, Jiajun Liang, Yangguang Li, Jiaheng Liu, Xintao Wang, Pengfei Wan, Di Zhang, Wanli Ouyang
  [Paper][Code][NeurIPS 2025]
• TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
  Yangguang Li, Zi-Xin Zou, Zexiang Liu, Dehu Wang, Yuan Liang, Zhipeng Yu, Xingchao Liu, Yuan-Chen Guo, Ding Liang, Wanli Ouyang, Yan-Pei Cao
  [Paper][Code][TPAMI 2025]
• ShapeGen: Towards High-Quality 3D Shape Synthesis
  Yangguang Li, Xianglong He, Zi-Xin Zou, Zexiang Liu, Wanli Ouyang, Ding Liang, Yan-Pei Cao
  [Paper][SIGGRAPH Asia 2025]
• SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling
  Xianglong He, Zi-Xin Zou, Chia-Hao Chen, Yuan-Chen Guo, Ding Liang, Chun Yuan, Wanli Ouyang, Yan-Pei Cao, Yangguang Li
  [Paper][Code][ICCV 2025 Oral]
• TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction
  Xuying Zhang, Yutong Liu, Yangguang Li, Renrui Zhang, Yufei Liu, Kai Wang, Wanli Ouyang, Zhiwei Xiong, Peng Gao, Qibin Hou, Ming-Ming Cheng
  [Paper][Code][ICCV 2025]
• Dreamcraft3d++: Efficient hierarchical 3d generation with multi-plane reconstruction model
  Jingxiang Sun, Cheng Peng, Ruizhi Shao, Yuan-Chen Guo, Xiaochen Zhao, Yangguang Li, Yanpei Cao, Bo Zhang, Yebin Liu
  [Paper][Code][TPAMI 2025]
• MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation
  Zehuan Huang, Yuan-Chen Guo, Xingqiao An, Yunhan Yang, Yangguang Li, Zi-Xin Zou, Ding Liang, Xihui Liu, Yan-Pei Cao, Lu Sheng
  [Paper][Code][CVPR 2025]
• PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
  Peng Li, Wangguandong Zheng, Yuan Liu, Tao Yu, Yangguang Li, Xingqun Qi, Xiaowei Chi, Siyu Xia, Yan-Pei Cao, Wei Xue, Wenhan Luo, Yike Guo
  [Paper][Code][CVPR 2025]
• TEXGen: a Generative Diffusion Model for Mesh Textures
  Xin Yu, Ze Yuan, Yuan-Chen Guo, Ying-Tian Liu, Jianhui Liu, Yangguang Li, Yan-Pei Cao, Ding Liang, Xiaojuan Qi
  [Paper][Code][TOG 2024 Best Paper Honorable Mention]
• Tripo Doodle: The Next-Gen AI 3D Creative Tool
  Sienna Hwang, Muqing Jia, Yan-Pei Cao, Yuan-Chen Guo, Yangguang Li, Ding Liang
  [Paper][Code][SIGGRAPH Asia 2024 Real-Time Live]
• Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
  Le Zhuo, Ruoyi Du, Han Xiao, Yangguang Li, Dongyang Liu, Rongjie Huang, Wenze Liu, Lirui Zhao, Fu-Yun Wang, Zhanyu Ma, Xu Luo, Zehan Wang, Kaipeng Zhang, Xiangyang Zhu, Si Liu, Xiangyu Yue, Dingning Liu, Wanli Ouyang, Ziwei Liu, Yu Qiao, Hongsheng Li, Peng Gao
  [Paper][Code][NeurIPS 2024]
• GVGEN: Text-to-3D Generation with Volumetric Representation
  Xianglong He, Junyi Chen, Sida Peng, Di Huang, Yangguang Li, Xiaoshui Huang, Chun Yuan, Wanli Ouyang, Tong He
  [Paper][Code][ECCV 2024]
• UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
  Zexiang Liu, Yangguang Li, Youtian Lin, Xin Yu, Sida Peng, Yan-Pei Cao, Xiaojuan Qi, Xiaoshui Huang, Ding Liang, Wanli Ouyang
  [Paper][Page][ECCV 2024]
• Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers
  Zi-Xin Zou, Zhipeng Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Yan-Pei Cao, Song-Hai Zhang
  [Paper][Code][CVPR 2024]
• EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion
  Zehuan Huang, Hao Wen, Junting Dong, Yaohui Wang, Yangguang Li, Xinyuan Chen, Yan-Pei Cao, Ding Liang, Yu Qiao, Bo Dai, Lu Sheng
  [Paper][Code][CVPR 2024]
• Text-to-3D with Classifier Score Distillation
  Xin Yu, Yuan-Chen Guo, Yangguang Li, Ding Liang, Song-Hai Zhang, Xiaojuan Qi
  [Paper][Code][ICLR 2024]
• Fast-BEV: A Fast and Strong Bird’s-Eye View Perception Baseline
  Yangguang Li, Bin Huang, Zeren Chen, Yufeng Cui, Feng Liang, Mingzhu Shen, Fenggang Liu, Enze Xie, Lu Sheng, Wanli Ouyang, Jing Shao
  [Paper][Code][TPAMI 2024]
• BEVBert: Multimodal Map Pre-training for Language-guided Navigation
  ong An, Yuankai Qi, Yangguang Li, Yan Huang, Liang Wang, Tieniu Tan, Jing Shao
  [Paper][Code][ICCV 2023]
• A Mixture of Surprises for Unsupervised Reinforcement Learning
  Andrew Zhao, Matthieu Gaetan Lin, Yangguang Li, Yong-Jin Liu, Gao Huang
  [Paper][Code][NeurIPS 2022]
• Towards Accurate Binary Neural Networks via Modeling Contextual Dependencies
  Xingrun Xing, Yangguang Li, Wei Li, Wenrui Ding, Yalong Jiang, Yufeng Wang, Jing Shao, Chunlei Liu, Xianglong Liu
  [Paper][Code][ECCV 2022]
• Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
  Yangguang Li, Feng Liang, Lichen Zhao, Yufeng Cui, Wanli Ouyang, Jing Shao, Fengwei Yu, Junjie Yan
  [Paper][Code][ICLR 2022]

• Serve as an area chair in NeurIPS.
• Serve as a reviewer in CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, etc.
• ECCV 2022: Workshop Organizers @ Computer Vision in the Wild.

• 2024.12: Best Paper Honorable Mention Award @ SIGGRAPH Asia 2024
• 2024.01: Best Poster Award @ AAAI 2024 Edge Intelligence Workshop
• 2023.01: SenseTime Team Award, SenseTime's highest award @2022 Autonomous Driving Mass Production projects
• 2022.06: 1st place in Embodied AI Workshop @ CVPR 2022
• 2022.06: 2nd place in UG2+ Challenge @ CVPR 2022
• 2022.01: SenseTime Team Award, SenseTime's highest award @2021 General Vision Big Models Technology System
• 2020.12: Outstanding Intern @SenseTime2020
• 2019.12: Outstanding Intern @SenseTime2019
• 2019.12: 1st place in Celebrity Video Identification Challenge @ACMMM 2019