| Infovae: Balancing learning and inference in variational autoencoders S Zhao, J Song, S Ermon Proceedings of the aaai conference on artificial intelligence 33, 5885-5892, 2019 | 290* | 2019 |
| Infogail: Interpretable imitation learning from visual demonstrations Y Li, J Song, S Ermon Advances in Neural Information Processing Systems, 3812-3822, 2017 | 217* | 2017 |
| Max-margin nonparametric latent feature models for link prediction J Zhu, J Song, B Chen arXiv preprint arXiv:1602.07428, 2016 | 101 | 2016 |
| Towards deeper understanding of variational autoencoding models S Zhao, J Song, S Ermon arXiv preprint arXiv:1702.08658, 2017 | 83 | 2017 |
| Learning hierarchical features from deep generative models S Zhao, J Song, S Ermon International Conference on Machine Learning, 4091-4099, 2017 | 82* | 2017 |
| A-nice-mc: Adversarial training for mcmc J Song, S Zhao, S Ermon Advances in Neural Information Processing Systems, 5140-5150, 2017 | 52 | 2017 |
| Multi-agent generative adversarial imitation learning J Song, H Ren, D Sadigh, S Ermon Advances in neural information processing systems, 7461-7472, 2018 | 51 | 2018 |
| Learning controllable fair representations J Song, P Kalluri, A Grover, S Zhao, S Ermon The 22nd International Conference on Artificial Intelligence and Statistics …, 2019 | 43 | 2019 |
| Bias correction of learned generative models using likelihood-free importance weighting A Grover, J Song, A Kapoor, K Tran, A Agarwal, EJ Horvitz, S Ermon Advances in Neural Information Processing Systems, 11058-11070, 2019 | 30 | 2019 |
| Bias and generalization in deep generative models: An empirical study S Zhao, H Ren, A Yuan, J Song, N Goodman, S Ermon Advances in Neural Information Processing Systems, 10792-10801, 2018 | 27 | 2018 |
| Understanding the limitations of variational mutual information estimators J Song, S Ermon arXiv preprint arXiv:1910.06222, 2019 | 26 | 2019 |
| The information autoencoding family: A lagrangian perspective on latent variable generative models S Zhao, J Song, S Ermon arXiv preprint arXiv:1806.06514, 2018 | 24 | 2018 |
| Multi-agent adversarial inverse reinforcement learning L Yu, J Song, S Ermon arXiv preprint arXiv:1907.13220, 2019 | 18 | 2019 |
| Calibrated model-based deep reinforcement learning A Malik, V Kuleshov, J Song, D Nemer, H Seymour, S Ermon arXiv preprint arXiv:1906.08312, 2019 | 14 | 2019 |
| Learning with weak supervision from physics and data-driven constraints H Ren, R Stewart, J Song, V Kuleshov, S Ermon AI Magazine 39 (1), 27-38, 2018 | 13 | 2018 |
| Factored temporal sigmoid belief networks for sequence learning J Song, Z Gan, L Carin International Conference on Machine Learning, 1272-1281, 2016 | 12 | 2016 |
| A theory of usable information under computational constraints Y Xu, S Zhao, J Song, R Stewart, S Ermon arXiv preprint arXiv:2002.10689, 2020 | 10 | 2020 |
| Adversarial constraint learning for structured prediction H Ren, R Stewart, J Song, V Kuleshov, S Ermon arXiv preprint arXiv:1805.10561, 2018 | 10 | 2018 |
| Training Deep Energy-Based Models with f-Divergence Minimization L Yu, Y Song, J Song, S Ermon arXiv preprint arXiv:2003.03463, 2020 | 8 | 2020 |
| Unsupervised Out-of-Distribution Detection with Batch Normalization J Song, Y Song, S Ermon arXiv preprint arXiv:1910.09115, 2019 | 8 | 2019 |
Stefano ErmonStanford UniversityVerified email at cs.stanford.edu
