I am a third year Ph.D. student in Stanford University. I think about problems in machine learning and deep learning under the supervision of Stefano Ermon. My publications cover topics such as deep generative models, Bayesian inference and (inverse) reinforcement learning and their applications.
I did my undergrad at Tsinghua University, where I was lucky enough to collaborate with Jun Zhu and Lawrence Carin on scalable Bayesian machine learning.
Contact: tsong at cs.stanford.edu
Robust and On-the-fly Dataset Denoising for Image Classification
Jiaming Song, Lunjia Hu, Michael Auli, Yann Dauphin, Tengyu Ma
To appear in the 16th European Conference on Computer Vision (ECCV 2020).
Bridging the Gap Between f-GANs and Wasserstein GANs
Jiaming Song, Stefano Ermon
In the 37th International Conference on Machine Learning (ICML 2020). [code] [slides]
Training Deep Energy-Based Models with f-Divergence Minimization
Lantao Yu, Yang Song, Jiaming Song, Stefano Ermon
In the 37th International Conference on Machine Learning (ICML 2020).
Domain Adaptive Imitation Learning
Kuno Kim, Yihong Gu, Jiaming Song, Shengjia Zhao, Stefano Ermon
In the 37th International Conference on Machine Learning (ICML 2020).
Unsupervised Out-of-distribution Detection with Batch Normalization
Jiaming Song, Yang Song, Stefano Ermon
In arXiv preprint arXiv:1910.09115.
Understanding the Limitations of Variational Mutual Information Estimators
Jiaming Song, Stefano Ermon
In the 8th International Conference on Learning Representations (ICLR 2020). [code] [slides]
A Theory of Usable Information under Computational Constraints
Yilun Xu, Shengjia Zhao, Jiaming Song, Russell Stweart, Stefano Ermon
In the 8th International Conference on Learning Representations (ICLR 2020). Oral presentation..
Chenlin Meng, Yang Song, Jiaming Song, Stefano Ermon
In the 23th International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
Permutation Invariant Graph Generation via Score-Based Generative Modeling
Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon
In the 23th International Conference on Artificial Intelligence and Statistics (AISTATS 2020).
Bias Correction of Learned Generative Models using Likelihood-free Importance Weighting
Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, Stefano Ermon
In the 32nd Neural Information Processing Systems (NeurIPS 2019).
Multi-Agent Adversarial Inverse Reinforcement Learning
Lantao Yu, Jiaming Song, Stefano Ermon
In the 36th International Conference on Machine Learning (ICML 2019). [code]
Calibrated Model-based Reinforcement Learning
Ali Malik, Volodymyr Kuleshov, Jiaming Song, Danny Nemer, Harlan Seymour, Stefano Ermon
In the 36th International Conference on Machine Learning (ICML 2019). [code]
Learning Controllable Fair Representations
Jiaming Song, Pratyusha Kalluri, Aditya Grover, Shengjia Zhao, Stefano Ermon
In the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019). [code]
Abridged in ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models.
InfoVAE: Information Maximizing Variational Autoencoders
Shengjia Zhao, Jiaming Song, Stefano Ermon
In the 33rd AAAI Conference on Artificial Intelligence (AAAI 2018). [blog]
Abridged in ICML Workshop on Theoretical Foundations and Applications of Deep Generative Models.
Multi-Agent Generative Adversarial Imitation Learning
Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon
In the 31th Neural Information Processing Systems (NeurIPS 2018). [code]
Abridged in the 6th International Conference on Learning Representations (ICLR 2018) Workshop Track, 1st Workshop on Goal Specifications for Reinforcement Learning.
Bias and Generalization in Deep Generative Models: An Empirical Study
Shengjia Zhao*, Hongyu Ren*, Arianna Yuan, Jiaming Song, Noah Goodman, Stefano Ermon
In the 31th Neural Information Processing Systems (NIPS 2018).. Spotlight Presentation. [code]
Learning with Weak Supervision from Physics and Data-Driven Constraints
Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon
In AI Magazine 39(1): 27-38.
A Lagrangian Perspective on Latent Variable Generative Models
Shengjia Zhao, Jiaming Song, Stefano Ermon
In the 2018 Conference on Uncertainty in Artificial Intelligence (UAI 2018). Oral Presentation. [code] [blog]
Abridged in 2018 Bay Area Machine Learning Symposium, ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models.
Accelerating Natural Gradient with Higher-Order Invariance
Yang Song, Jiaming Song, Stefano Ermon
In the 35th International Conference on Machine Learning (ICML 2018). [code] [blog]
Adversarial Constraint Learning for Structured Prediction
Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon
In 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018). [code]
Abridged in NIPS Workshop on Learning with Limited Data.
A-NICE-MC: Adversarial Training for MCMC
Jiaming Song, Shengjia Zhao, Stefano Ermon
In the 30th Neural Information Processing Systems (NIPS 2017). [code] [slides] [blog]
Abridged in ICML 2017 Workshop on Implicit Models.
InfoGAIL: Interpretable Imitation Learning from Visual Demonstration
Yunzhu Li, Jiaming Song, Stefano Ermon
In the 30th Neural Information Processing Systems (NIPS 2017). [code]
Learning Hierarchical Features from Generative Models
Shengjia Zhao, Jiaming Song, Stefano Ermon
In the 34th International Conference on Machine Learning (ICML 2017). [code] [blog]
Factored Sigmoid Belief Networks for Sequence Learning
Jiaming Song, Zhe Gan, Lawrence Carin
In 33rd International Conference on Machine Learning (ICML 2016).
Organizational Churn: A Roll of the Dice?
Canyao Liu*, Jiaming Song*, Chuan Yu*
In Undergraduate Mathematics and its Applications (UMAP), Issue 36.2. Invited paper.
Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation
Bei Chen, Ning Chen, Jun Zhu, Jiaming Song, Bo Zhang
In 10th Association for the Advancement of Artificial Intelligence Conference (AAAI 2016).
Dual Optimization for Latent Variable Generative Models
Shengjia Zhao*, Jiaming Song*, Stefano Ermon
In ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models.
Markov Chain Monte Carlo for Learning Belief Networks
Laetitia Shao*, Jiaming Song*, Aditya Grover, Stefano Ermon
In ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models.
Structured Prediction with Adversarial Constraint Learning
Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon
In NIPS 2017 Workshop on Learning with Limited Data.
A Lagrangian Perspective on Latent Variable Generative Modeling
Shengjia Zhao, Jiaming Song, Stefano Ermon
In NIPS 2017 Workshop on Bayesian Deep Learning.
An Empirical Study of the Generalization Behavior of Generative Adversarial Networks
Hongyu Ren, Shengjia Zhao, Jiaming Song, Lijie Fan, Stefano Ermon
In NIPS 2017 Workshop on Deep Learning: Bridging Theory and Practice.
Generative Adversarial Learning of Markov Chains
Jiaming Song, Shengjia Zhao, Stefano Ermon
In the 5th International Conference on Learning Representations (ICLR 2017) Workshop. [code]
Max-Margin Nonparametric Latent Feature Relational Models for Link Prediction
Jun Zhu, Jiaming Song, Bei Chen
In arXiv preprint arXiv:1602.07428.
Torwards Deeper Understanding of Variational Autoencoding Models
Shengjia Zhao, Jiaming Song, Stefano Ermon
In arXiv preprint arXiv:1702.08658.