profile.jpg

Yang Song (宋飏)

Research Scientist at OpenAI.

Incoming Assistant Professor,
Electrical Engineering and Computing + Mathematical Sciences,
California Institute of Technology (Caltech).

Research: As a researcher in machine learning, I am focused on developing scalable methods for modeling, analyzing and generating complex, high-dimensional data. My interest spans multiple areas, including generative modeling, representation learning, probabilistic inference, AI safety, and AI for science. My ultimate goal is to address problems that have wide-ranging significance, develop methods that are both accessible and effective, and build intelligent systems that can improve human lives.

Previously: I received my Ph.D. in Computer Science from Stanford University, advised by Stefano Ermon. I was a research intern at Google Brain, Uber ATG, and Microsoft Research. I obtained my Bachelor’s degree in Mathematics and Physics from Tsinghua University, where I worked with Jun Zhu, Raquel Urtasun, and Richard Zemel.

news

Jan 3, 2023 Quanta magazine just released an article on diffusion models, featuring some of my early contributions in the field. Read the story here.
Sep 30, 2022 I will be joining the Department of Electrical Engineering (EE) and Department of Computing + Mathematical Sciences (CMS) at California Institute of Technology as an Assistant Professor starting from January 2024. I am currently seeking self-motivated Ph.D. students and postdoctoral fellows to join my research group in Fall 2023. Candidates with backgrounds in CS, EE, mathematics, physics, or statistics are especially encouraged to apply. If you are interested in working with me as a Ph.D. student, please apply to Caltech CMS/EE and mention my name in your applications. If you are interested in a postdoc position, please contact me directly.
Aug 30, 2022 We are organizing a workshop on score-based methods at NeurIPS 2022. Check out our website for details!

selected publications [full list]

(*) denotes equal contribution

  1. arXiv
    Improved Techniques for Training Consistency Models
    Yang Song, and Prafulla Dhariwal
    arXiv:2310.14189
  2. ICML
    Consistency Models
    In the 40th International Conference on Machine Learning, 2023.
  3. Thesis
    Learning to Generate Data by Estimating Gradients of the Data Distribution
    Yang Song
    Stanford University
  4. ICLR
    Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
    Yang Song*, Liyue Shen*, Lei Xing, and Stefano Ermon
    In the 10th International Conference on Learning Representations, 2022. Abridged in the NeurIPS 2021 Workshop on Deep Learning and Inverse Problems.
  5. NeurIPSSpotlight
    Maximum Likelihood Training of Score-Based Diffusion Models
    Yang Song*, Conor Durkan*, Iain Murray, and Stefano Ermon
    In the 35th Conference on Neural Information Processing Systems, 2021.
    Spotlight Presentation [top 3%]
  6. ICML
    Accelerating Feedforward Computation via Parallel Nonlinear Equation Solving
    Yang Song, Chenlin Meng, Renjie Liao, and Stefano Ermon
    In the 38th International Conference on Machine Learning, 2021.
  7. ICLROralAward
    Score-Based Generative Modeling through Stochastic Differential Equations
    In the 9th International Conference on Learning Representations, 2021.
    Outstanding Paper Award
  8. NeurIPS
    Improved Techniques for Training Score-Based Generative Models
    Yang Song, and Stefano Ermon
    In the 34th Conference on Neural Information Processing Systems, 2020.
  9. NeurIPSOral
    Generative Modeling by Estimating Gradients of the Data Distribution
    Yang Song, and Stefano Ermon
    In the 33rd Conference on Neural Information Processing Systems, 2019.
    Oral Presentation [top 0.5%]
  10. UAIOral
    Sliced Score Matching: A Scalable Approach to Density and Score Estimation
    Yang Song*, Sahaj Garg*, Jiaxin Shi, and Stefano Ermon
    In the 35th Conference on Uncertainty in Artificial Intelligence, 2019.
    Oral Presentation [top 8.7%]
  11. NeurIPS
    Constructing Unrestricted Adversarial Examples with Generative Models
    Yang Song, Rui Shu, Nate Kushman, and Stefano Ermon
    In the 32nd Conference on Neural Information Processing Systems, 2018.
  12. ICLR
    PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examples
    Yang Song, Taesup Kim, Sebastian NowozinStefano Ermon, and Nate Kushman
    In the 6th International Conference on Learning Representations, 2018.