About me

Hi, I am Yilun Xu. I am a fourth year PhD student in MIT, advised by Tommi Jaakkola. I obtained my Bachelor’s degree from Turing Class in EECS dept, Peking University. I had the privilege of working with Yizhou Wang in PKU, and Stefano Ermon in Stanford.

My research interests are machine learning, with a current emphasis on generative modeling: (i) new family of generative models; (ii) improving the training, sampling and controllability of generative models, e.g. PFGM and diffusion models. Previously, I worked on bridging machine learning and information theory.

Contact: ylxu@mit.edu , xuyilun@pku.edu.cn

Publications

(*) denotes equal contribution

  • Restart Sampling for Improving Generative Processes
    Yilun Xu*, Mingyang Deng*, Xiang Cheng*, Yonglong Tian, Ziming Liu, Tommi Jaakkola.
    In Neural Information Processing Systems (NeurIPS), 2023.
    [PDF] ,[Code]
    News Coverage: [MarkTechPost],
    Star
  • PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
    Yilun Xu, Ziming Liu, Yonglong Tian, Shangyuan Tong, Max Tegmark, Tommi Jaakkola.
    In International Conference on Machine Learning (ICML), 2023.
    [PDF] ,[Code] ,[Slide]
    News Coverage: [Quanta Magazine], [Jiangmen Venture (CN)]
    Star
    PWC
  • GenPhys: From Physical Processes to Generative Models
    Ziming Liu, Di Luo, Yilun Xu, Tommi Jaakkola, Max Tegmark.
    In preprint, 2023
    [PDF]
    News Coverage: [Quanta Magazine],
  • Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
    Yilun Xu*, Shangyuan Tong*, Tommi Jaakkola.
    In International Conference on Learning Representations (ICLR), 2023
    [PDF] ,[Code] ,[Slide] ,[Poster]
    News Coverage: [MarkTechPost],
    Star
  • Poisson Flow Generative Models
    Yilun Xu*, Ziming Liu*, Max Tegmark, Tommi Jaakkola.
    In Neural Information Processing Systems (NeurIPS), 2022. (Spotlight)
    [PDF] ,[Code] ,[Slide] ,[Poster]
    News Coverage: [Quanta Magazine], [AssemblyAI Blog], [MarkTechPost], [Synced (CN)], [PaperWeekly (CN)], [QbitAI (CN)],
    Star
  • Controlling Directions Orthogonal to a Classifier
    Yilun Xu, Hao He, Tianxiao Shen, Tommi Jaakkola.
    In International Conference on Learning Representations (ICLR), 2022. (Spotlight)
    [PDF] ,[Code] ,[Slide] ,[Poster]
    Star
  • A Survey on Generative Diffusion Model
    Hanqun Cao, Cheng Tan, Zhangyang Gao, Yilun Xu, Guangyong Chen, Pheng-Ann Heng, Stan Z. Li.
    In preprint, 2022
    [PDF] ,[Code]
    Star
  • Learning Representations that Support Robust Transfer of Predictors
    Yilun Xu, Tommi Jaakkola.
    In preprint, 2022
    [PDF] ,[Code]
  • Can Subnetwork Structure Be the Key to Out-of-Distribution Generalization?
    Dinghuai Zhang, Kartik Ahuja, Yilun Xu, Yisen Wang, Aaron Courville.
    In International Conference on Machine Learning (ICML), 2021. (Long talk)
    [PDF]
  • Anytime Sampling for Autoregressive Models via Ordered Autoencoding
    Yilun Xu, Yang Song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon.
    In International Conference on Learning Representations (ICLR), 2021
    [PDF] ,[Code] ,[Slide] ,[Poster]
    Star
  • A Theory of Usable Information under Computational Constraints
    Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon.
    In International Conference on Learning Representations (ICLR), 2020. (Oral)
    [PDF] ,[Code] ,[Slide] ,[Video]
    News Coverage: [Synced (CN)],
  • TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
    Xinwei Sun*, Yilun Xu*, Peng Cao, Yuqing Kong, Lingjing Hu, Shanghang Zhang, Yizhou Wang.
    In European Conference on Computer Vision (ECCV), 2020. (Oral)
    [PDF] ,[Code]
  • L_{DMI} : A Novel Information-theoretic Loss Function for Training Deep Nets Robust to Label Noise
    Yilun Xu*, Peng Cao*, Yuqing Kong, Yizhou Wang.
    In Neural Information Processing Systems (NeurIPS), 2019
    [PDF] ,[Code] ,[Slide]
    News Coverage: [Synced (CN)], [PKU-CFCS News (CN)]
    Star
  • Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
    Peng Cao*, Yilun Xu*, Yuqing Kong, Yizhou Wang.
    In International Conference on Learning Representations (ICLR), 2019
    [PDF] ,[Code] ,[Slide]
    News Coverage: [PKU-CFCS News (CN)]
    Star

Education

    Sept. 2021* - : Massachusetts Institute of Technology, Boston

     PhD student

     Advisor: Tommi Jaakkola

     *: remote during Sept 2020 - Aug 2021

   Sept. 2016 - July. 2020: Peking University, Beijing

     B.S. in Turing Class, Computer Science (summa cum laude)

     Advisor: Yizhou Wang

   Jun. 2019 - Sept. 2019: Stanford University, Palo Alto

     Visiting student

     Advisor: Stefano Ermon


Work Experience

   Jun. 2023 - now: NVIDIA

     Research Intern

     Advisor: Karsten Kreis and Arash Vahdat


Talk

  • Peking University, CFCS, Aug 2023

    Unlocking the Potential of Physics-Inspired Generative Models,

  • NVIDIA Research, July 2023

    Unlocking the Potential of Physics-Inspired Generative Models,

  • ByteDance, AI for Science Team, July 2023

    Unlocking the Potential of Physics-Inspired Generative Models,

  • Swarma Club, May 2023

    Unlocking the Potential of Physics-Inspired Generative Models, [Slide] [Video (CN)]

  • TechBeat/Jiangmen Ventures, April 2023

    Unlocking the Potential of Physics-Inspired Generative Models, [Slide] [Video (CN)]

  • MLTea Talk, MIT, April 2023

    Unlocking the Potential of Physics-Inspired Generative Models, [Slide]

  • Guest lecturer at 6.S052/6.S952: Modeling with Machine learning for CS, MIT, April 2023

    Conditional and Controllable Generation, [Slide]

  • Stanford University, hosted by Prof. Mert Pilanci, Feb 2023

    Unlocking the Potential of Physics-Inspired Generative Models, [Slide]

  • AssemblyAI AI Hackathon, Dec 2022

    Poisson Flow Generative Models, [Slide]

  • Princeton University, hosted by Prof. Mengdi Wang, Nov 2022

    Poisson Flow Generative Models (and beyond), [Slide]

  • MIT NetMIT Group, hosted by Prof. Dina Katabi, Nov 2022

    Poisson Flow Generative Models (and beyond)

  • AI TIME, June 2022

    Controlling Directions Orthogonal to a Classifier, [Slide]

  • AI TIME, June 2021

    Anytime Sampling for Autoregressive Models via Ordered Autoencoding, [Slide]

Service

Conference Reviewer: NeurIPS 2020, 2021, 2022, 2023; ICLR 2021, 2022, 2023; ICML 2021, 2022, 2023

Workshop Reviewer: ICML-AI4Science 20220

Journal Reviewer: TMLR, TPAMI

PC member: ICLR 2022 PAIR2Struct Workshop

Panelist: ICML 2023 Workshop on Structured Probabilistic Inference & Generative Modeling

Teaching Assistant for 6.S052/6.S952: Modeling with Machine learning for CS, MIT, Spring 2023 (co-design the problem set and lectures for this new course, and receive an outstanding TA rating of 6.9 out of 7.0 from students)

Miscellaneous

I am a national second-class table tennis player in China. Men’s single champion in PKU Freshman’s Cup (2016). I also played for MIT table tennis team, winning the 3rd place (group) in the 2022 NCTTA Upper New England Championship.

I have been playing PUBG (mobile), LoL a lot. Find me out!