| Ffjord: Free-form continuous dynamics for scalable reversible generative models W Grathwohl, RTQ Chen, J Bettencourt, I Sutskever, D Duvenaud arXiv preprint arXiv:1810.01367, 2018 | 696* | 2018 |
| Invertible residual networks J Behrmann, W Grathwohl, RTQ Chen, D Duvenaud, JH Jacobsen International Conference on Machine Learning, 573-582, 2019 | 474 | 2019 |
| Your classifier is secretly an energy based model and you should treat it like one W Grathwohl, KC Wang, JH Jacobsen, D Duvenaud, M Norouzi, ... arXiv preprint arXiv:1912.03263, 2019 | 375 | 2019 |
| Backpropagation through the void: Optimizing control variates for black-box gradient estimation W Grathwohl, D Choi, Y Wu, G Roeder, D Duvenaud arXiv preprint arXiv:1711.00123, 2017 | 263 | 2017 |
| Learning the Stein Discrepancy for Training and Evaluating Energy-Based Models without Sampling W Grathwohl, KC Wang, JH Jacobsen, D Duvenaud, R Zemel International Conference on Machine Learning, 2020 | 76* | 2020 |
| Deep reinforcement learning and simulation as a path toward precision medicine BK Petersen, J Yang, WS Grathwohl, C Cockrell, C Santiago, G An, ... Journal of Computational Biology 26 (6), 597-604, 2019 | 71* | 2019 |
| Oops i took a gradient: Scalable sampling for discrete distributions W Grathwohl, K Swersky, M Hashemi, D Duvenaud, C Maddison International Conference on Machine Learning, 3831-3841, 2021 | 51 | 2021 |
| Understanding the limitations of conditional generative models E Fetaya, JH Jacobsen, W Grathwohl, R Zemel arXiv preprint arXiv:1906.01171, 2019 | 37* | 2019 |
| Disentangling space and time in video with hierarchical variational auto-encoders W Grathwohl, A Wilson arXiv preprint arXiv:1612.04440, 2016 | 24 | 2016 |
| Continuous diffusion for categorical data S Dieleman, L Sartran, A Roshannai, N Savinov, Y Ganin, PH Richemond, ... arXiv preprint arXiv:2211.15089, 2022 | 16 | 2022 |
| Joint energy-based models for semi-supervised classification S Zhao, JH Jacobsen, W Grathwohl ICML 2020 Workshop on Uncertainty and Robustness in Deep Learning 1, 2020 | 12 | 2020 |
| Gradient-based optimization of neural network architecture W Grathwohl, E Creager, SKS Ghasemipour, R Zemel | 12 | 2018 |
| Optimal design of stochastic DNA synthesis protocols based on generative sequence models EN Weinstein, AN Amin, WS Grathwohl, D Kassler, J Disset, D Marks International Conference on Artificial Intelligence and Statistics, 7450-7482, 2022 | 9 | 2022 |
| Self-conditioned embedding diffusion for text generation R Strudel, C Tallec, F Altché, Y Du, Y Ganin, A Mensch, W Grathwohl, ... arXiv preprint arXiv:2211.04236, 2022 | 6 | 2022 |
| No MCMC for me: Amortized samplers for fast and stable training of energy-based models D Duvenaud, J Kelly, K Swersky, M Hashemi, M Norouzi, W Grathwohl | 6 | 2021 |
| Reduce, reuse, recycle: Compositional generation with Energy-Based diffusion models and MCMC Y Du, C Durkan, R Strudel, JB Tenenbaum, S Dieleman, R Fergus, ... arXiv preprint arXiv:2302.11552, 2023 | 5 | 2023 |
| Score-based diffusion meets annealed importance sampling A Doucet, W Grathwohl, AG Matthews, H Strathmann Advances in Neural Information Processing Systems 35, 21482-21494, 2022 | 5 | 2022 |
| Annealed Importance Sampling meets Score Matching A Doucet, WS Grathwohl, AGG Matthews, H Strathmann ICLR Workshop on Deep Generative Models for Highly Structured Data, 2022 | 4 | 2022 |
| No conditional models for me: Training joint ebms on mixed continuous and discrete data J Kelly, WS Grathwohl Energy Based Models Workshop-ICLR 2021, 2021 | 4 | 2021 |
| Directly training joint energy-based models for conditional synthesis and calibrated prediction of multi-attribute data J Kelly, R Zemel, W Grathwohl arXiv preprint arXiv:2108.04227, 2021 | 3 | 2021 |
David DuvenaudAssociate Professor, University of TorontoVerified email at cs.toronto.edu
