Ph.D. Candidate, Computer Science
Stanford Artificial Intelligence Laboratory
Statistical Machine Learning Group
Curriculum Vitae


I am a fifth year Ph.D. candidate in Computer Science in Stanford University, advised by Stefano Ermon. I did my undergrad in the Department of Computer Science and Technology, Tsinghua University, where I worked with Jun Zhu and Lawrence Carin.

My research is centered on deep unsupervised learning, with various applications on deep generative modeling, representation learning and (inverse) reinforcement learning. Recently, I am interested in the following topics:

  • Information-theoretic approaches to machine learning and representation learning [1, 2, 3, 4]
  • Improvements to generative modeling and statistical inference [1, 2, 3, 4]
  • Learning complex behaviors and intentions from demonstrations [1, 2, 3, 4]
  • Societal issues in machine learning, such as fairness and calibration [1, 2, 3]

Email: tsong [at] cs [dot] stanford [dot] edu


Teaching
  • CS228, Probablistic Graphical Models (Winter 2020, Head TA)
  • CS236, Deep Generative Models (Fall 2018, TA)

Publications

2020

  1. [35]
    Jiaming Song, Stefano Ermon Multi-label Contrastive Predictive Coding NeurIPS 2020, In Neural Information Processing Systems, (Oral presentation).
  2. [34]
    Chenlin Meng, Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon Autoregressive Score Matching NeurIPS 2020, In Neural Information Processing Systems.
  3. [33]
    Jonathan Kuck, Shuvam Chakraborty, Hao Tang, Rachel Luo, Jiaming Song, Ashish Sabharwal, Stefano Ermon Belief Propagation Neural Networks NeurIPS 2020, In Neural Information Processing Systems.
  4. [23]
    Jiaming Song, Chenlin Meng, Stefano Ermon Denoising Diffusion Implicit Models January, arXiv:2010.02502. [code]
  5. [32]
    Jiaming Song, Michael Auli, Yann Dauphin, Tengyu Ma Robust and On-the-fly Dataset Denoising for Image Classification ECCV 2020, In European Conference on Computer Vision. [slides]
  6. [31]
    Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon Permutation Invariant Graph Generation via Score-Based Generative Modeling AISTATS 2020, In International Conference on Artificial Intelligence and Statistics. [code]
  7. [30]
    Chenlin Meng, Yang Song, Jiaming Song, Stefano Ermon Gaussianization Flows AISTATS 2020, In International Conference on Artificial Intelligence and Statistics. [code]
  8. [29]
    Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon Training Deep Energy-Based Models with f-Divergence Minimization ICML 2020, In International Conference on Machine Learning.
  9. [28]
    Jiaming Song, Stefano Ermon Bridging the Gap Between f-GANs and Wasserstein GANs ICML 2020, In International Conference on Machine Learning. [slides] [code]
  10. [27]
    Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon Domain Adaptive Imitation Learning ICML 2020, In International Conference on Machine Learning.
  11. [26]
    Jiaming Song, Stefano Ermon Understanding the Limitations of Variational Mutual Information Estimators ICLR 2020, In International Conference on Learning Representations. [slides] [code]
  12. [25]
    Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stewart, Stefano Ermon A Theory of Usable Information under Computational Constraints ICLR 2020, In International Conference on Learning Representations, (Oral presentation).
  13. [24]
    Nate Gruver, Jiaming Song, Mykel J Kochenderfer, Stefano Ermon Multi-agent Adversarial Inverse Reinforcement Learning with Latent Variables AAMAS 2020, In International Conference on Autonomous Agents and MultiAgent Systems (extended abstract).
  14. [21]
    Rachel Luo, Shengjia Zhao, Jiaming Song, Jonathan Kuck, Stefano Ermon, Silvio Savarese Privacy Preserving Recalibration under Domain Shift Preprint, arXiv:2008.09643.
  15. [20]
    Samarth Sinha*, Jiaming Song*, Animesh Garg, Stefano Ermon Experience Replay with Likelihood-free Importance Weights Preprint, arXiv:2006.13169.

2019

  1. [19]
    Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric J Horvitz, Stefano Ermon Bias Correction of Learned Generative Models using Likelihood-free Importance Weighting NeurIPS 2019, In Advances in Neural Information Processing Systems.
  2. [18]
    Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon Calibrated Model-based Deep Reinforcement Learning ICML 2019, In International Conference on Machine Learning. [code]
  3. [17]
    Lantao Yu, Jiaming Song, Stefano Ermon Multi-agent Adversarial Inverse Reinforcement Learning ICML 2019, In International Conference on Machine Learning. [code]
  4. [16]
    Shengjia Zhao, Jiaming Song, Stefano Ermon InfoVAE: Balancing Learning and Inference in Variational Autoencoders AAAI 2019, In AAAI Conference on Artificial Intelligence.
  5. [15]
    Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, Stefano Ermon Learning Controllable Fair Representations AISTATS 2019, In International Conference on Artificial Intelligence and Statistics. [code]
  6. [14]
    Jiaming Song, Yang Song, Stefano Ermon Unsupervised Out-of-Distribution Detection with Batch Normalization Preprint, arXiv:1910.09115.

2018

  1. [13]
    Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon Multi-Agent Generative Adversarial Imitation Learning NeurIPS 2018, In Advances in Neural Information Processing Systems. [code]
  2. [12]
    Shengjia Zhao, Hongyu Ren, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon Bias and Generalization in Deep Generative Models: An Empirical Study NeurIPS 2018, In Advances in Neural Information Processing Systems, (Spotlight presentation). [code]
  3. [11]
    Shengjia Zhao, Jiaming Song, Stefano Ermon The Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models UAI 2018, In Conference on Uncertainty in Artificial Intelligence, (Oral presentation). [code]
  4. [10]
    Yang Song, Jiaming Song, Stefano Ermon Accelerating Natural Gradient with Higher-Order Invariance ICML 2018, In International Conference on Machine Learning. [code]
  5. [9]
    Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon Adversarial Constraint Learning for Structured Prediction IJCAI 2018, In International Joint Conference on Artificial Intelligence. [code]
  6. [8]
    Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon Learning with weak supervision from physics and data-driven constraints AI Magazine, AI Magazine.

2017

  1. [7]
    Jiaming Song, Shengjia Zhao, Stefano Ermon A-NICE-MC: Adversarial training for MCMC NeurIPS 2017, In Advances in Neural Information Processing Systems. [slides] [code] [blog]
  2. [5]
    Yunzhu Li, Jiaming Song, Stefano Ermon InfoGAIL: Interpretable imitation learning from visual demonstrations NeurIPS 2017, In Advances in Neural Information Processing Systems. [code]
  3. [6]
    Shengjia Zhao, Jiaming Song, Stefano Ermon Learning Hierarchical Features from Deep Generative Models ICML 2017, In International Conference on Machine Learning. [code]
  4. [4]
    Shengjia Zhao, Jiaming Song, Stefano Ermon Towards deeper understanding of variational autoencoding models Preprint, arXiv:1702.08658.

2016

  1. [3]
    Jiaming Song, Zhe Gan, Lawrence Carin Factored Temporal Sigmoid Belief Networks for Sequence Learning ICML 2016, In International Conference on Machine Learning.
  2. [2]
    Bei Chen, Ning Chen, Jun Zhu, Jiaming Song, Bo Zhang Discriminative nonparametric latent feature relational models with data augmentation AAAI 2016, In AAAI Conference on Artificial Intelligence.
  3. [1]
    Jun Zhu, Jiaming Song, Bei Chen Max-margin Nonparametric Latent Feature Models for Link Prediction Preprint, arXiv:1602.07428.

Professional Services

Journal reviewer: IEEE TPAMI, JAIR, IEEE TIT, ACM TIST

Conference reviewer / Program committee: ICML (2019, 2020), NeurIPS (2019, 2020), ICLR (2018, 2019, 2020, 2021), COLT (2019), UAI (2019, 2020), CVPR (2020, 2021), ECCV (2020), ICCV (2019), AAAI (2021), ACML (2018, 2019), WACV (2020)

Workshop organization:


Awards and Fellowships
  • Qualcomm Innovation Fellowship (QInF 2018, 4.6%)
  • Stanford School of Engineering Fellowship (2016)
  • Google Excellence Scholarship (2015)
  • Outstanding Undergraduate, China Computer Federation (2015)
  • Outstanding Winner, Interdisciplinary Contest in Modeling (2015, 0.4%)
  • Zhong Shimo Scholarship (2013, 0.75%)

Acknowledgements: based on the al-folio template by Maruan Al-Shedivat.