Xian Liu

Member of Technical Staff
xAI
Seattle, WA

E-mail  /  CV  /  Google Scholar  /  Github  /  Twitter  /  LinkedIn

Biography

I am a Member of Technical Staff at xAI, working on the Omni Model Pretraining and Visual Generation. Before that, I was a Research Scientist at NVIDIA Research. I obtained Bachelor's degree at Zhejiang University in 2021, and Ph.D. degree at The Chinese University of Hong Kong (CUHK), Multi-Media Laboratory (MMLab) in 2025.

My research interest lies in Multi-Modal AI and Foundation Generative Models, with focus on GenAI pre/post-training, visual tokenizers, and their applications. I was the core contributor to NVIDIA Cosmos series GitHub stars , an ensemble of open-source world foundation models including visual tokenizers, image / video foundation models, VLMs, and their post-trained variants.

News

  • [12/2025] Join xAI as Member of Technical Staff, working on Omni and Visual Generation models. Stay tuned for our release!
  • [11/2025] We release Cosmos 2.5, an improved version of world foundation model. Check our Github and technical report.
  • [09/2025] One paper is accepted to NeurIPS 2025.
  • [07/2025] One paper is accepted to ICCV 2025 with oral presentation.
  • [06/2025] Pass my Ph.D. defense and become Dr. Liu officially!
[Show more]

Industrial Research

Cosmos: World Foundation Model Platform for Physical AI
NVIDIA Cosmos Team: Xian Liu (Core Contributor).
Contributions: Auto-Regressive Foundation Model Pre-Training & Post-Training. (CES'25 Best of AI, Best Overall)
Cosmos 2.5: Improved World Simulation with Video Foundation Models for Physical AI
NVIDIA Cosmos Team: Xian Liu (Core Contributor).
Contributions: Data Processing Pipelines, Captioning, Long Video Generation, Evaluation, Transfer Post-training.
Cosmos Tokenizer: A Suite of Image and Video Neural Tokenizers
NVIDIA Cosmos Team: Xian Liu (Core Contributor).
Contributions: Continuous/Discrete Image/Video Tokenizers.
Cosmos-Transfer: World Generation with Adaptive Multimodal Control
NVIDIA Cosmos Team: Xian Liu (Core Contributor).
Contributions: Adaptive Multi-Modal Control, Data Processing Pipelines, Open-Source Repo.

Selected Publications [ Full List ] (* indicates equal contribution)

HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
Xian Liu, Xiaohang Zhan, Jiaxiang Tang, Ying Shan, Gang Zeng, Dahua Lin, Xihui Liu, Ziwei Liu.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024. (Highlight, Top 2.8%)
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
Xian Liu, Jian Ren, Aliaksandr Siarohin, Ivan Skorokhodov, Yanyu Li, Dahua Lin, Xihui Liu, Ziwei Liu, Sergey Tulyakov.
International Conference on Learning Representations (ICLR), 2024. (Review Score 6, 6, 8, 10, Top 1.6%, Rank)
Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation
Xian Liu, Yinghao Xu, Qianyi Wu, Hang Zhou, Wayne Wu, Bolei Zhou.
European Conference on Computer Vision (ECCV), 2022. (Oral, Top 2.7%)
Audio-Driven Co-Speech Gesture Video Generation
Xian Liu, Qianyi Wu, Hang Zhou, Yuanqi Du, Wayne Wu, Dahua Lin, Ziwei Liu.
Advances in Neural Information Processing Systems (NeurIPS), 2022. (Spotlight, Top 5%)
HMAR: Efficient Hierarchical Masked AutoRegressive Image Generation
Hermann Kumbong*, Xian Liu*, Tsung-Yi Lin, Xihui Liu, Ziwei Liu, Daniel Y. Fu, Ming-Yu Liu, Christopher Ré, David W. Romero.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025.
TC4D: Trajectory-Conditioned Text-to-4D Generation
Sherwin Bahmani*, Xian Liu*, Yifan Wang*, Ivan Skorokhodov, Victor Rong, Ziwei Liu, Xihui Liu, Jeong Joon Park, Sergey Tulyakov, Gordon Wetzstein, Andrea Tagliasacchi, David B. Lindell.
European Conference on Computer Vision (ECCV), 2024.

Working Experiences

xAI
Member of Technical Staff.
Dec. 2025 - Now
xAI, Omni Pretrain Team.
NVIDIA
Research Scientist.
Jun. 2024 - Dec. 2025
NVIDIA Research, Cosmos Team.

Internship Experiences

NVIDIA
Generative AI Research Intern.
Mar. 2024 - Jun. 2024
NVIDIA Research, Deep Imagination Group.
University of Toronto
Research Visiting Student.
Dec. 2023 - Mar. 2024
UofT, Toronto Computational Imaging Group.
Tencent AI Lab
Research Intern.
Sept. 2023 - Dec. 2023
Tencent AI Laboratory.
Supervisor: Xiaohang Zhan, Ying Shan.
Snap Research
Research Intern.
May. 2023 - Sept. 2023
Snap Research, Creative Vision Group.
Shanghai AI Lab
Research Intern.
Jul. 2021 - Feb. 2022
Shanghai AI Lab, Digital Content Group.
Supervisor: Hang Zhou, Wayne Wu.
SenseTime
Research Intern.
Aug. 2020 - Jun. 2021
SenseTime Research, Intelligent Video Group.
Supervisor: Qianyi Wu, Bo Dai.

Invited Talks

Professional Services

  • Area Chair / Senior Program Committee: AAAI.
  • Conference Reviewer: CVPR, ECCV, ICCV, WACV, SIGGRAPH, SIGGRAPH Asia, NeurIPS, ICML, ICLR, AISTATS, AAAI, ACM MM.
  • Journal Reviewer: TPAMI, IJCV, TVCG, TIP, TMM, EG, CGF, PG.

Selected Honors & Awards

  • CNET 2025 Best of CES, Best of AI, and Best Overall.
    2025
  • ECCV Outstanding Reviewer Award.
    2024
  • CVPR Travel Award.
    2024
  • ICLR Travel Award.
    2024
  • National Scholarship.
    2019, 2020
  • Hong Kong Ph.D. Fellowship Scheme (HKPFS).
    2021- 2025
  • Outstanding Graduate of Zhejiang Province.
    2021
  • Outstanding Bachelor Thesis Award of Zhejiang University, Top 1%.
    2021
  • UCLA CSST Scholarship Program.
    2020
  • SenseTime Scholarship.
    2020
  • Tang Lixin Scholarship.
    2019
  • First Class Scholarship for Academic Excellence.
    2019, 2020

Teaching Experience

  • ENGG 1120, Linear Algebra for Engineers.
    Spring 2022.
  • ENGG 2440, Discrete Mathematics for Engineers.
    Fall 2021.