| Improving factuality and reasoning in language models through multiagent debate Y Du, S Li, A Torralba, JB Tenenbaum, I Mordatch Forty-first International Conference on Machine Learning, 2023 | 1377 | 2023 |
| Joint detection and identification feature learning for person search T Xiao*, S Li*, B Wang, L Lin, X Wang Computer Vision and Pattern Recognition (CVPR), 2017, 2017 | 1354* | 2017 |
| Compositional Visual Generation with Composable Diffusion Models N Liu*, S Li*, Y Du*, A Torralba, JB Tenenbaum Proceedings of the European Conference on Computer Vision (ECCV), 2022, 2022 | 676 | 2022 |
| Learning Feature Pyramids for Human Pose Estimation W Yang, S Li, W Ouyang, H Li, X Wang International Conference on Computer Vision (ICCV), 2017, 2017 | 674 | 2017 |
| Person search with natural language description S Li, T Xiao, H Li, B Zhou, D Yue, X Wang Computer Vision and Pattern Recognition (CVPR), 2017, 2017 | 652 | 2017 |
| Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification S Li, S Bak, P Carr, X Wang Computer Vision and Pattern Recognition (CVPR), 2018, 2018 | 465 | 2018 |
| Pre-Trained Language Models for Interactive Decision-Making L Shuang, P Xavier, P Chris, D Yilun, W Clinton, F Linxi, C Tao, H De-An, ... NeurIPS 2022, 2022 | 363* | 2022 |
| Identity-Aware Textual-Visual Matching with Latent Co-attention S Li, T Xiao, H Li, W Yang, X Wang International Conference on Computer Vision (ICCV), 2017, 2017 | 339 | 2017 |
| Conceptfusion: Open-set multimodal 3d mapping KM Jatavallabhula, A Kuwajerwala, Q Gu, M Omama, T Chen, A Maalouf, ... arXiv preprint arXiv:2302.07241, 2023 | 337 | 2023 |
| Compositional visual generation with energy based models Y Du, S Li, I Mordatch Advances in Neural Information Processing Systems 33, 2020 | 243* | 2020 |
| Watch-and-help: A challenge for social perception and human-AI collaboration X Puig, T Shu, S Li, Z Wang, YH Liao, JB Tenenbaum, S Fidler, A Torralba ICLR 2021, 2020 | 203 | 2020 |
| Improved Contrastive Divergence Training of Energy Based Models Y Du, S Li, J Tenenbaum, I Mordatch ICML 2021, 2020 | 192 | 2020 |
| 3D Neural Scene Representations for Visuomotor Control Y Li*, S Li*, V Sitzmann, P Agrawal, A Torralba Conference on Robot Learning, 112-123, 2022 | 175 | 2022 |
| Compositional Foundation Models for Hierarchical Planning A Ajay, S Han, Y Du, S Li, A Gupta, T Jaakkola, J Tenenbaum, L Kaelbling, ... arXiv preprint arXiv:2309.08587, 2023 | 127* | 2023 |
| Learning to Compose Visual Relations N Liu*, S Li*, Y Du*, J Tenenbaum, A Torralba Advances in Neural Information Processing Systems 34, 2021 | 116* | 2021 |
| Unsupervised learning of compositional energy concepts Y Du, S Li, Y Sharma, J Tenenbaum, I Mordatch Advances in Neural Information Processing Systems 34, 15608-15620, 2021 | 101 | 2021 |
| Question-Guided Hybrid Convolution for Visual Question Answering P Gao, H Li, S Li, P Lu, Y LI, S Hoi, X Wang Proceedings of the European Conference on Computer Vision (ECCV), 469-485, 2018 | 96 | 2018 |
| Unified video action model S Li, Y Gao, D Sadigh, S Song arXiv preprint arXiv:2503.00200, 2025 | 66 | 2025 |
| Energy-Based Models for Continual Learning S Li, Y Du, GM van de Ven, I Mordatch Conference on Lifelong Learning Agents, 2020 | 65* | 2020 |
| Multiagent finetuning: Self improvement with diverse reasoning chains V Subramaniam, Y Du, JB Tenenbaum, A Torralba, S Li, I Mordatch arXiv preprint arXiv:2501.05707, 2025 | 62* | 2025 |
Antonio TorralbaProfessor of Computer Science, MITVerified email at csail.mit.edu
