avatar

Siqiao Huang

Undergraduate Student
Tsinghua University
huang-sq23@mails.tsinghua.edu.cn


About Me

I’m currently a senior undergraduate student (from 2023 Fall) in IIIS (Yao Class), Tsinghua University, pursuing a Bachelor’s degree in Computer Science and Technology.

Currently, I am serving as a research intern at WEIRD Lab, University of Washington, under the supervision of Prof. Abhishek Gupta. Prior to this, I was extremely fortunate to be advised by Prof. Max Simchowitz, where I spent an amazing summer at CMU MLD. I am also deeply honored for the experience of working with Prof. Hang Zhao and Prof. Mingsheng Long.

I am currently seeking a PhD position starting in 2027 Fall, and am happy to discuss potential research fit and collaboration opportunities.

Some picture options: ( I'll try to keep this up to date)
📷 Photos are taken within the past year.
Photo with Prof. Yann LeCun @ AMI Mixup
(this will probably be here for a while) 😝
Poster session at ICLR'26 🙌
Giving a talk on my recent work (first from the right) 🗣️
At the Andy Worhol Museum @ Pittsburgh 👨‍🎨
Golden Gate Bridge 🌉

Research Interests

My research aims to develop foundation models with intrinsic understandings of the physical world and apply them to enable general-purpose decision-making. My research focuses on:

News

Older News
  • [Aug. 2025] 🐋 SURGE is accepted by EMNLP 2025 Main, with a top 0.3% meta score!
  • [May. 2025] 🔥 I became a member of the Sparking Program, the most prestigious and selective academic organization for students at Tsinghua University (top 1%).
  • [May. 2025] 📈 TrajWorld is accepted by ICML, 2025.
  • [Jan. 2025] 📜 My personal blog website is officially online!
  • [Nov. 2024] 🏆 Honored to receive Comprehensive Excellence Award of Tsinghua.
  • [Nov. 2024] 🏆 Glad to receive Outstanding Sports Scholarship of Tsinghua.

Education

Publications

* equal contribution † project lead ‡ corresponding author

|
  1. OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining teaser ArXiv
    OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining
    Yuran Wang*†, Siqiao Huang*†, Mingleyang Li*, Chenhao Zhang*, Jiaqi Liang*, ..., Xiaowei Chi, Guanqi He, Shanghang Zhang, Hao Dong, Lin Shao‡, Hang Zhao‡
    ArXiv preprint, 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  2. OMG: Omni-Modal Motion Generation for Generalist Humanoid Control teaser ArXiv
    OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
    Siqiao Huang*, Kun-Ying Lee*, Dongming Qiao*, Guanqi He*, Zhenyu Wang, Yitang Li, Shaoting Zhu, Hang Zhao‡
    Arxiv Preprint, 2026.
    ExWBC @ RSS 2026 Oral, RoboData @ RSS 2026 Spotlight.
    arXiv PDF Code Project Page
  3. Nano World Models: A Minimalist Implementation of Future Video Prediction teaser ArXiv
    Nano World Models: A Minimalist Implementation of Future Video Prediction
    Siqiao Huang, Partha Kaushik, Michael Chen, Hengkai Pan, Kaiwen Geng, Omar Chehab, Fernando Moreno-Pino, Max Simchowitz‡
    Technical Report, 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  4. MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI teaser NeurIPS
    MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
    Bohan Lyu*, Yucheng Yang*, Siqiao Huang*, Jiaru Zhang*, ..., Max Simchowitz, Jiantao Jiao, Dawn Song, Chi Jin‡
    NeurIPS 2026 Evaluations & Datasets Track (Oral).
    arXiv PDF Code Project Page BibTex Huggingface
  5. Vid2World: Crafting Video Diffusion Models to Interactive World Models teaser ICLR
    Vid2World: Crafting Video Diffusion Models to Interactive World Models
    Siqiao Huang*, Jialong Wu*, Qixing Zhou, Shangchen Miao, Mingsheng Long‡
    ICLR 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  1. GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives teaser ArXiv
    GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
    Qize Yu*†, Lianrui Fan*, Boyu Chen*, Jiaqi Liang*, Xini Ding*, ..., Siqiao Huang, ..., Ping Luo‡, Shiyu Huang‡
    ArXiv preprint, 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  2. WB-WAM: Heterogeneous Body–Hand Pre-training for Humanoid Loco-Manipulation teaser ArXiv
    WB-WAM: Heterogeneous Body–Hand Pre-training for Humanoid Loco-Manipulation
    Chuan Qin*, Shaoting Zhu*, Siyuan Luo, Siqiao Huang, Hongyu Zhao, Shanaka Baduge, Hang Zhao‡
    ArXiv preprint, 2026.
    arXiv PDF Project Page BibTex Huggingface
  3. OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining teaser ArXiv
    OpenWAM: An Open, Modular Exploration Towards Systematic World–Action Model Pretraining
    Yuran Wang*†, Siqiao Huang*†, Mingleyang Li*, Chenhao Zhang*, Jiaqi Liang*, ..., Xiaowei Chi, Guanqi He, Shanghang Zhang, Hao Dong, Lin Shao‡, Hang Zhao‡
    ArXiv preprint, 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  4. HarnessEval-W: Agentifying the Evaluation of Visual Worlds teaser ArXiv
    HarnessEval-W: Agentifying the Evaluation of Visual Worlds
    Weiliang Chen*, Haowen Sun*, Jun Gao*†, ..., Siqiao Huang, ..., Jialong Wu†, Jiangran Lyu†, Fangfu Liu†
    ArXiv preprint, 2026.
    arXiv PDF Code Project Page
  5. OMG: Omni-Modal Motion Generation for Generalist Humanoid Control teaser ArXiv
    OMG: Omni-Modal Motion Generation for Generalist Humanoid Control
    Siqiao Huang*, Kun-Ying Lee*, Dongming Qiao*, Guanqi He*, Zhenyu Wang, Yitang Li, Shaoting Zhu, Hang Zhao‡
    Arxiv Preprint, 2026.
    ExWBC @ RSS 2026 Oral, RoboData @ RSS 2026 Spotlight.
    arXiv PDF Code Project Page
  6. Nano World Models: A Minimalist Implementation of Future Video Prediction teaser ArXiv
    Nano World Models: A Minimalist Implementation of Future Video Prediction
    Siqiao Huang, Partha Kaushik, Michael Chen, Hengkai Pan, Kaiwen Geng, Omar Chehab, Fernando Moreno-Pino, Max Simchowitz‡
    Technical Report, 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  7. MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI teaser NeurIPS
    MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI
    Bohan Lyu*, Yucheng Yang*, Siqiao Huang*, Jiaru Zhang*, ..., Max Simchowitz, Jiantao Jiao, Dawn Song, Chi Jin‡
    NeurIPS 2026 Evaluations & Datasets Track (Oral).
    arXiv PDF Code Project Page BibTex Huggingface
  8. Vid2World: Crafting Video Diffusion Models to Interactive World Models teaser ICLR
    Vid2World: Crafting Video Diffusion Models to Interactive World Models
    Siqiao Huang*, Jialong Wu*, Qixing Zhou, Shangchen Miao, Mingsheng Long‡
    ICLR 2026.
    arXiv PDF Code Project Page BibTex Huggingface
  9. SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors teaser EMNLP
    SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors
    Bohan Lyu*, Siqiao Huang*, Zichen Liang*, Qian Sun, Jiaming Zhang
    EMNLP 2025 Main, Top 0.3% Meta Score.
    arXiv PDF Code BibTex Huggingface
  10. Trajectory World Models for Heterogeneous Environments teaser ICML
    Trajectory World Models for Heterogeneous Environments
    Shaofeng Yin*, Jialong Wu*, Siqiao Huang, Xingjian Su, Xu He, Jianye Hao, Mingsheng Long‡
    ICML 2025.
    arXiv PDF Code BibTex

Selected Projects

  1. Awesome World Models 🌍 GitHub stars
    A curated list of awesome works in world modeling, aiming to serve as a one-stop resource for everyone interested in world modeling. [🧵 Twitter Thread]
    Code Project Page  Hot! 100+ Stars in under 24 Hours!
  2. Nano World Models 🌎 GitHub stars
    A minimalist, batteries-included repo for training, evaluating, and deploying diffusion-forcing-based world models toward open, reproducible world model science.
    Code Project Page BibTex arXiv PDF Hugging Face

Experience


Academic Experience

  1. WEIRD Lab, University of Washington
    Research Intern: 2026.3 - Present.
    Topics: Robot Manipulation, Test-time Adaptation, VLA, World Models, Real-World RL, Science of Robotics.
    Research Advisor: Prof. Abhishek Gupta.
  2. Machine Learning Department, CMU
    Research Intern: 2025.6 - 2026.3.
    Topics: World Models, Generative Models, Learning in Sequential Environments and Dynamical Systems.
    Research Advisor: Prof. Max Simchowitz.
  3. MARS Lab, Tsinghua University
    Research Intern: 2025.9 - Present.
    Topics: Humanoid Foundation Models, VLAs, Generative Control Policies.
    Research Advisor: Prof. Hang Zhao.
  4. Tsinghua Machine Learning Group (THUML)
    Research Intern: 2024.7 - 2025.8.
    Topics: World Models, Sequential Modeling.
    Research Advisor: Prof. Mingsheng Long.

Industry Experience

  1. Wuji Technology
    Research Scientist: 2026.1 - 2026.4.
    WAM Team Lead. Topics: Dexterous Manipulation, Video-Centric Generalist Policies, Robot Foundation Models.

Honors & Awards

Professional Services

Teaching Assistant

Reviewer

Language

Miscs



Powered by Jekyll and Minimal Light theme.