| L_dmi: A novel information-theoretic loss function for training deep nets robust to label noise Y Xu, P Cao, Y Kong, Y Wang Advances in neural information processing systems 32, 2019 | 247* | 2019 |
| A survey on generative diffusion model H Cao, C Tan, Z Gao, Y Xu, G Chen, PA Heng, SZ Li arXiv preprint arXiv:2209.02646, 2022 | 155 | 2022 |
| A theory of usable information under computational constraints Y Xu, S Zhao, J Song, R Stewart, S Ermon International Conference on Learning Representations (ICLR 2020), 2020 | 131 | 2020 |
| Can subnetwork structure be the key to out-of-distribution generalization? D Zhang, K Ahuja, Y Xu, Y Wang, A Courville International Conference on Machine Learning, 12356-12367, 2021 | 83 | 2021 |
| Poisson flow generative models Y Xu, Z Liu, M Tegmark, T Jaakkola Advances in Neural Information Processing Systems 35, 16782-16795, 2022 | 51 | 2022 |
| Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds P Cao, Y Xu, Y Kong, Y Wang International Conference on Learning Representations (ICLR 2019), 2018 | 42 | 2018 |
| Pfgm++: Unlocking the potential of physics-inspired generative models Y Xu, Z Liu, Y Tian, S Tong, M Tegmark, T Jaakkola International Conference on Machine Learning (ICML), 2023, 2023 | 26 | 2023 |
| Controlling directions orthogonal to a classifier Y Xu, H He, T Shen, T Jaakkola International Conference on Learning Representations (ICLR 2022), 2022 | 20 | 2022 |
| Tcgm: An information-theoretic framework for semi-supervised multi-modality learning X Sun, Y Xu, P Cao, Y Kong, L Hu, S Zhang, Y Wang Computer Vision–ECCV 2020: 16th European Conference, Glasgow, UK, August 23 …, 2020 | 20 | 2020 |
| Restart Sampling for Improving Generative Processes Y Xu, M Deng, X Cheng, Y Tian, Z Liu, T Jaakkola Advances in Neural Information Processing Systems 36 (NeurIPS 2023), 2023 | 19 | 2023 |
| Learning representations that support robust transfer of predictors Y Xu, T Jaakkola arXiv preprint arXiv:2110.09940, 2021 | 18 | 2021 |
| Anytime sampling for autoregressive models via ordered autoencoding Y Xu, Y Song, S Garg, L Gong, R Shu, A Grover, S Ermon International Conference on Learning Representations (ICLR 2021), 2021 | 15 | 2021 |
| Stable target field for reduced variance score estimation in diffusion models Y Xu, S Tong, T Jaakkola International Conference on Learning Representations (ICLR 2023), 2023 | 11 | 2023 |
| Genphys: From physical processes to generative models Z Liu, D Luo, Y Xu, T Jaakkola, M Tegmark arXiv preprint arXiv:2304.02637, 2023 | 6 | 2023 |
| Particle guidance: non-iid diverse sampling with diffusion models G Corso, Y Xu, V De Bortoli, R Barzilay, T Jaakkola arXiv preprint arXiv:2310.13102, 2023 | 2 | 2023 |
Tommi JaakkolaMITVerified email at csail.mit.edu
