| Gemini: a family of highly capable multimodal models G Team, R Anil, S Borgeaud, JB Alayrac, J Yu, R Soricut, J Schalkwyk, ... arXiv preprint arXiv:2312.11805, 2023 | 3253 | 2023 |
| Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context G Team, P Georgiev, VI Lei, R Burnell, L Bai, A Gulati, G Tanzer, ... arXiv preprint arXiv:2403.05530, 2024 | 1159 | 2024 |
| Deep ensembles: A loss landscape perspective S Fort, H Hu, B Lakshminarayanan arXiv preprint arXiv:1912.02757, 2019 | 695 | 2019 |
| Plex: Towards reliability using pretrained large model extensions D Tran, J Liu, MW Dusenberry, D Phan, M Collier, J Ren, K Han, Z Wang, ... arXiv preprint arXiv:2207.07411, 2022 | 125 | 2022 |
| Wide neural networks forget less catastrophically SI Mirzadeh, A Chaudhry, D Yin, H Hu, R Pascanu, D Gorur, M Farajtabar International Conference on Machine Learning, 15699-15717, 2022 | 72 | 2022 |
| A method based on total variation for network modularity optimization using the MBO scheme H Hu, T Laurent, MA Porter, AL Bertozzi SIAM Journal on Applied Mathematics 73 (6), 2224-2246, 2013 | 61 | 2013 |
| Multi-class graph Mumford-Shah model for plume detection using the MBO scheme H Hu, J Sunu, AL Bertozzi International Workshop on Energy Minimization Methods in Computer Vision and …, 2015 | 59 | 2015 |
| End-to-end interpretation of the french street name signs dataset R Smith, C Gu, DS Lee, H Hu, R Unnikrishnan, J Ibarz, S Arnoud, S Lin Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8 …, 2016 | 58 | 2016 |
| Information-theoretic online memory selection for continual learning S Sun, D Calandriello, H Hu, A Li, M Titsias arXiv preprint arXiv:2204.04763, 2022 | 52 | 2022 |
| Deep ensembles: A loss landscape perspective. arXiv 2019 S Fort, H Hu, B Lakshminarayanan arXiv preprint arXiv:1912.02757, 2019 | 46 | 2019 |
| Cross-view policy learning for street navigation A Li, H Hu, P Mirowski, M Farajtabar Proceedings of the IEEE/CVF international conference on computer vision …, 2019 | 34 | 2019 |
| Task-agnostic continual learning with hybrid probabilistic models P Kirichenko, M Farajtabar, D Rao, B Lakshminarayanan, N Levine, A Li, ... arXiv preprint arXiv:2106.12772, 2021 | 22 | 2021 |
| Multislice modularity optimization in community detection and image segmentation H Hu, Y van Gennip, B Hunter, AL Bertozzi, MA Porter 2012 IEEE 12th International Conference on Data Mining Workshops, 934-936, 2012 | 22 | 2012 |
| Deep ensembles: a loss landscape perspective. arXiv S Fort, H Hu, B Lakshminarayanan arXiv preprint arXiv:1912.02757, 2019 | 18 | 2019 |
| One pass imagenet H Hu, A Li, D Calandriello, D Gorur arXiv preprint arXiv:2111.01956, 2021 | 17 | 2021 |
| Learning from delayed outcomes via proxies with applications to recommender systems TA Mann, S Gowal, A Gyorgy, H Hu, R Jiang, B Lakshminarayanan, ... International Conference on Machine Learning, 4324-4332, 2019 | 14 | 2019 |
| Learning from delayed outcomes with intermediate observations TA Mann, S Gowal, R Jiang, H Hu, B Lakshminarayanan, A Gyorgy arXiv preprint arXiv:1807.09387, 2018 | 10 | 2018 |
| Geosocial graph-based community detection Y van Gennip, H Hu, B Hunter, MA Porter 2012 IEEE 12th International Conference on Data Mining Workshops, 754-758, 2012 | 10 | 2012 |
| Learning from delayed outcomes using neural networks H Hu, R Jiang, TA Mann, SA Gowal, B Lakshminarayanan, A György US Patent 11,714,994, 2023 | 8 | 2023 |
| An incremental reseeding strategy for clustering X Bresson, H Hu, T Laurent, A Szlam, J von Brecht Imaging, Vision and Learning Based on Optimization and PDEs: IVLOPDE, Bergen …, 2018 | 7 | 2018 |
