About me

Hi, I am Yilun Xu, a research scientist in NVIDIA Research, fundamental GenAI team.

📢 🔥 We are hiring research scientist/intern working on diffusion acceleration (e.g., one-step distillation)! Please consider reaching out to me if you are interested!

I received my PhD in MIT EECS, 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. I also worked with Karsten Kreis and Arash Vahdat in NVIDIA Research, during summer 2023.

My research interests are machine learning, with a current emphasis on deep generative modeling:

• (i) New models: PFGM [10], PFGM++ [13], HGF [18], t-EDM [21]
• (ii) Training: STF [11], Disco-Diff [16], Style Control [9]
• (iii) Sampling: Restart sampling [14], Particle Guidance [15], Anytime AR [5]
• (iv) Discrete diffusion: DDPD [19], EDLM [20]
• (v) Diffusion Distillation: TCM [22], f-distill [23]

Previously, I worked on bridging machine learning and information theory [4, 3, 2, 1].

Contact: yilunx@nvidia.com, ylxu@mit.edu , xuyilun@pku.edu.cn

Publications

(*) denotes equal contribution

1. COSMOS-NANO
   NVIDIA et al.
   In preparation, coming soon. Featured in Jensen Huang's CES / GTC 2025 keynote.
   [PDF]
2. One-step Diffusion Models with f-Divergence Distribution Matching
   Yilun Xu, Weili Nie, Arash Vahdat.
   In preprint, coming soon
   [PDF] ,[Project Page]
3. Truncated Consistency Models
   Sangyun Lee, Yilun Xu, Tomas Geffner, Giulia Fanti, Karsten Kreis, Arash Vahdat, Weili Nie.
   In International Conference on Learning Representations (ICLR), 2025
   [PDF] ,[Code] ,[Project Page]
4. Heavy-Tailed Diffusion Models
   Kushagra Pandey, Jaideep Pathak, Yilun Xu, Stephan Mandt, Michael Pritchard, Arash Vahdat, Morteza Mardani.
   In International Conference on Learning Representations (ICLR), 2025
   [PDF]
5. Energy-Based Diffusion Language Models for Text Generation
   Minkai Xu, Tomas Geffner, Karsten Kreis, Weili Nie, Yilun Xu, Jure Leskovec, Stefano Ermon, Arash Vahdat.
   In International Conference on Learning Representations (ICLR), 2025
   [PDF]
6. Think While You Generate: Discrete Diffusion with Planned Denoising
   Sulin Liu, Juno Nam, Andrew Campbell, Hannes Stärk, Yilun Xu, Tommi Jaakkola, Rafael Gómez-Bombarelli.
   In International Conference on Learning Representations (ICLR), 2025
   [PDF]
7. Hamiltonian Score Matching and Generative Flows
   Peter Holderrieth, Yilun Xu, Tommi Jaakkola.
   In Neural Information Processing Systems (NeurIPS), 2024.
   [PDF]
8. On Physics-Inspired Generative Models
   Yilun Xu.
   PhD Thesis 🎓, Massachusetts Institute of Technology.
   [PDF]
9. DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
   Yilun Xu, Gabriele Corso, Tommi Jaakkola, Arash Vahdat, Karsten Kreis.
   In International Conference on Machine Learning (ICML), 2024.
   [PDF] ,[Project Page]
   
10. Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
    Gabriele Corso, Yilun Xu, Valentin De Bortoli, Regina Barzilay, Tommi Jaakkola.
    In International Conference on Learning Representations (ICLR), 2024; Deep Inverse Workshop, Neural Information Processing Systems (NeurIPS), 2023 (Oral); Workshop on Diffusion Models, Neural Information Processing Systems (NeurIPS), 2023.
    [PDF] ,[Code]
    Star
11. 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
12. 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: [MIT News], [Quanta Magazine], [Jiangmen Venture (CN)]
    Star
    
13. GenPhys: From Physical Processes to Generative Models
    Ziming Liu, Di Luo, Yilun Xu, Tommi Jaakkola, Max Tegmark.
    In preprint, 2023
    [PDF]
    News Coverage: [MIT News], [Quanta Magazine],
14. 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
15. 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: [MIT News], [Quanta Magazine], [AssemblyAI Blog], [MarkTechPost], [Synced (CN)], [PaperWeekly (CN)], [QbitAI (CN)],
    Star
16. 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
17. A Survey on Generative Diffusion Model
    Hanqun Cao, Cheng Tan, Zhangyang Gao, Yilun Xu, Guangyong Chen, Pheng-Ann Heng, Stan Z. Li.
    In IEEE Transactions on Knowledge and Data Engineering (TKDE), 2023.
    [PDF] ,[Code]
    Star
18. Learning Representations that Support Robust Transfer of Predictors
    Yilun Xu, Tommi Jaakkola.
    In preprint, 2022
    [PDF] ,[Code]
19. 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]
20. 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
21. 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)],
22. 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]
23. 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
24. 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

    Sep. 2021* - May. 2024: Massachusetts Institute of Technology

     Ph.D. in Computer Science

     Advisor: Tommi Jaakkola

     *: remote during Sept 2020 - Aug 2021

   Sep. 2016 - July. 2020: Peking University

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

     Advisor: Yizhou Wang

   Jun. 2019 - Sep. 2019: Stanford University

     Visiting reseacher

     Advisor: Stefano Ermon

Work Experience

   Jun. 2023 - May, 2024: NVIDIA

     Research Intern

     Advisor: Karsten Kreis and Arash Vahdat

Talks

• On Physics-Inspired Generative Models

  • Peking University, hosted by Prof. Yizhou Wang, June 2024 [Video (CN)], [Slide]

  • CUHK, hosted by Prof. Pheng Ann Heng, June 2024

• Generative Models & Physical Processes
  • UCLA, hosted by Prof. Yingnian Wu, Oct 2023 [Slide]
• Unlocking the Potential of Physics-Inspired Generative Models
  • Learning on Graphs and Geometry seminar. Oct, 2023 [Video]

  • Zhejiang University, hosted by Prof. Chao Xu, Oct 2023

  • Peking University, CFCS, Aug 2023

  • NVIDIA Research, July 2023

  • ByteDance, AI for Science Team, July 2023

  • Swarma Club, May 2023, [Slide] [Video (CN)]

  • TechBeat/Jiangmen Ventures, April 2023, [Slide] [Video (CN)]

  • MLTea Talk, MIT, April 2023, [Slide]
  • Stanford University, hosted by Prof. Mert Pilanci, Feb 2023, [Slide]
• Conditional and Controllable Generation
  • Guest lecturer at 6.S052/6.S952: Modeling with Machine learning for CS, MIT, April 2023, [Slide]
• Poisson Flow Generative Models

  • AssemblyAI AI Hackathon, Dec 2022, [Slide]

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

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

• Controlling Directions Orthogonal to a Classifier,
  • AI TIME, June 2022, [Slide]
• Anytime Sampling for Autoregressive Models via Ordered Autoencoding
  • AI TIME, June 2021, [Slide]

Service

Conference Reviewer: NeurIPS 2020, 2021, 2022, 2023; ICLR 2021, 2022, 2023, 2024; ICML 2021, 2022, 2023

Workshop Reviewer: ICML-AI4Science 2022

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!