| Pixeldefend: Leveraging generative models to understand and defend against adversarial examples Y Song, T Kim, S Nowozin, S Ermon, N Kushman International Conference on Learning Representations, 2018 | 682 | 2018 |
| Generative modeling by estimating gradients of the data distribution Y Song, S Ermon Advances in Neural Information Processing Systems, 11918-11930, 2019 | 658 | 2019 |
| Score-Based Generative Modeling through Stochastic Differential Equations Y Song, J Sohl-Dickstein, DP Kingma, A Kumar, S Ermon, B Poole International Conference on Learning Representations, 2021 | 590 | 2021 |
| Constructing Unrestricted Adversarial Examples with Generative Models Y Song, R Shu, N Kushman, S Ermon Advances in Neural Information Processing Systems, 8322-8333, 2018 | 235 | 2018 |
| Improved techniques for training score-based generative models Y Song, S Ermon Advances in Neural Information Processing Systems 33, 2020 | 231 | 2020 |
| Efficient graph generation with graph recurrent attention networks R Liao, Y Li, Y Song, S Wang, W Hamilton, DK Duvenaud, R Urtasun, ... Advances in Neural Information Processing Systems, 4255-4265, 2019 | 205 | 2019 |
| SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations C Meng, Y He, Y Song, J Song, J Wu, JY Zhu, S Ermon International Conference on Learning Representations, 2021 | 124* | 2021 |
| Sliced score matching: A scalable approach to density and score estimation Y Song, S Garg, J Shi, S Ermon Uncertainty in Artificial Intelligence, 574-584, 2019 | 123 | 2019 |
| Training deep neural networks via direct loss minimization Y Song, A Schwing, R Zemel, R Urtasun International Conference on Machine Learning, 2169-2177, 2016 | 101 | 2016 |
| Maximum Likelihood Training of Score-Based Diffusion Models Y Song, C Durkan, I Murray, S Ermon arXiv preprint arXiv:2101.09258, 2021 | 96* | 2021 |
| How to Train Your Energy-Based Models Y Song, DP Kingma arXiv preprint arXiv:2101.03288, 2021 | 91 | 2021 |
| GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation M Xu, L Yu, Y Song, C Shi, S Ermon, J Tang International Conference on Learning Representations, 2021 | 66 | 2021 |
| Permutation invariant graph generation via score-Based generative modeling C Niu, Y Song, J Song, S Zhao, A Grover, S Ermon International Conference on Artificial Intelligence and Statistics, 4474-4484, 2020 | 58 | 2020 |
| Solving Inverse Problems in Medical Imaging with Score-Based Generative Models Y Song, L Shen, L Xing, S Ermon arXiv preprint arXiv:2111.08005, 2021 | 53 | 2021 |
| Diversity can be Transferred: Output Diversification for White-and Black-box Attacks Y Tashiro, Y Song, S Ermon Advances in Neural Information Processing Systems 33, 2020 | 51* | 2020 |
| Mintnet: Building invertible neural networks with masked convolutions Y Song, C Meng, S Ermon Advances in Neural Information Processing Systems, 11004-11014, 2019 | 50 | 2019 |
| Learning Energy-Based Models by Diffusion Recovery Likelihood R Gao, Y Song, B Poole, YN Wu, DP Kingma International Conference on Learning Representations, 2020 | 43 | 2020 |
| CSDI: Conditional score-based diffusion models for probabilistic time series imputation Y Tashiro, J Song, Y Song, S Ermon Advances in Neural Information Processing Systems 34, 24804-24816, 2021 | 37 | 2021 |
| Diffusion models: A comprehensive survey of methods and applications L Yang, Z Zhang, Y Song, S Hong, R Xu, Y Zhao, Y Shao, W Zhang, B Cui, ... arXiv preprint arXiv:2209.00796, 2022 | 36 | 2022 |
| Stochastic gradient geodesic mcmc methods C Liu, J Zhu, Y Song Advances in neural information processing systems 29, 3009-3017, 2016 | 32 | 2016 |
Stefano ErmonStanford UniversityVerified email at cs.stanford.edu
