| Natural language descriptions of deep visual features E Hernandez, S Schwettmann, D Bau, T Bagashvili, A Torralba, J Andreas International Conference on Learning Representations, 2021 | 126 | 2021 |
| Invariant representations of mass in the human brain S Schwettmann, JB Tenenbaum, N Kanwisher Elife 8, e46619, 2019 | 58 | 2019 |
| Multimodal neurons in pretrained text-only transformers S Schwettmann, N Chowdhury, S Klein, D Bau, A Torralba Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023 | 21 | 2023 |
| The role of multiple neuromodulators in reinforcement learning that is based on competition between eligibility traces MA Huertas, SE Schwettmann, HZ Shouval Frontiers in synaptic neuroscience 8, 37, 2016 | 20 | 2016 |
| Find: A function description benchmark for evaluating interpretability methods S Schwettmann, T Shaham, J Materzynska, N Chowdhury, S Li, J Andreas, ... Advances in Neural Information Processing Systems 36, 2024 | 19 | 2024 |
| Toward a visual concept vocabulary for gan latent space S Schwettmann, E Hernandez, D Bau, S Klein, J Andreas, A Torralba Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 17 | 2021 |
| A multimodal automated interpretability agent TR Shaham, S Schwettmann, F Wang, A Rajaram, E Hernandez, ... Forty-first International Conference on Machine Learning, 2024 | 15 | 2024 |
| Evidence for an Intuitive Physics Engine in the Human Brain. S Schwettmann, J Fischer, J Tenenbaum, N Kanwisher CogSci, 2018 | 10 | 2018 |
| Stable reinforcement learning via temporal competition between LTP and LTD traces MA Huertas, S Schwettmann, A Kirkwood, H Shouval BMC Neuroscience 15, 1-1, 2014 | 6 | 2014 |
| Neural representation of the intuitive physical dimension of mass S Schwettmann, J Fischer, J Tenenbaum, N Kanwisher Journal of Vision 18 (10), 731-731, 2018 | 2 | 2018 |
| Eliciting language model behaviors with investigator agents XL Li, N Chowdhury, DD Johnson, T Hashimoto, P Liang, S Schwettmann, ... arXiv preprint arXiv:2502.01236, 2025 | 1 | 2025 |
| Nearest Neighbor Normalization Improves Multimodal Retrieval N Chowdhury, F Wang, S Shenoy, D Kiela, S Schwettmann, T Thrush arXiv preprint arXiv:2410.24114, 2024 | 1 | 2024 |
| Automatic Discovery of Visual Circuits A Rajaram, N Chowdhury, A Torralba, J Andreas, S Schwettmann arXiv preprint arXiv:2404.14349, 2024 | 1 | 2024 |
| An Alternative to Regulation: The Case for Public AI N Vincent, D Bau, S Schwettmann, J Tan arXiv preprint arXiv:2311.11350, 2023 | 1 | 2023 |
| A Function Interpretation Benchmark for Evaluating Interpretability Methods S Schwettmann, TR Shaham, J Materzynska, N Chowdhury, S Li, ... arXiv preprint arXiv:2309.03886, 2023 | 1 | 2023 |
| A Multimodal Automated Interpretability Agent T Rott Shaham, S Schwettmann, F Wang, A Rajaram, E Hernandez, ... arXiv e-prints, arXiv: 2404.14394, 2024 | | 2024 |
| Generalizable Representations for Vision in Biological and Artificial Neural Networks SE Schwettmann Massachusetts Institute of Technology, 2021 | | 2021 |
| Latent Compass: Creation by Navigation S Schwettmann, H Strobelt, M Martino arXiv preprint arXiv:2012.14283, 2020 | | 2020 |
Antonio TorralbaProfessor of Computer Science, MIT確認したメール アドレス: csail.mit.edu