| Sagedb: A learned database system T Kraska, M Alizadeh, A Beutel, EH Chi, J Ding, A Kristo, G Leclerc, ... | 202 | 2021 |
| Datamodels: Predicting predictions from training data A Ilyas, SM Park, L Engstrom, G Leclerc, A Madry arXiv preprint arXiv:2202.00622, 2022 | 70 | 2022 |
| 3db: A framework for debugging computer vision models G Leclerc, H Salman, A Ilyas, S Vemprala, L Engstrom, V Vineet, K Xiao, ... Advances in Neural Information Processing Systems 35, 8498-8511, 2022 | 44 | 2022 |
| Raising the cost of malicious ai-powered image editing H Salman, A Khaddaj, G Leclerc, A Ilyas, A Madry arXiv preprint arXiv:2302.06588, 2023 | 39 | 2023 |
| FFCV: Accelerating training by removing data bottlenecks G Leclerc, A Ilyas, L Engstrom, SM Park, H Salman, A Mądry Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 36 | 2023 |
| Trak: Attributing model behavior at scale SM Park, K Georgiev, A Ilyas, G Leclerc, A Madry arXiv preprint arXiv:2303.14186, 2023 | 35 | 2023 |
| Adversarially trained neural representations are already as robust as biological neural representations C Guo, M Lee, G Leclerc, J Dapello, Y Rao, A Madry, J Dicarlo International Conference on Machine Learning, 8072-8081, 2022 | 33 | 2022 |
| The two regimes of deep network training G Leclerc, A Madry arXiv preprint arXiv:2002.10376, 2020 | 33 | 2020 |
| Datamodels: Understanding predictions with data and data with predictions A Ilyas, SM Park, L Engstrom, G Leclerc, A Madry International Conference on Machine Learning, 9525-9587, 2022 | 21 | 2022 |
| The seamless peer and cloud evolution framework G Leclerc, JE Auerbach, G Iacca, D Floreano Proceedings of the Genetic and Evolutionary Computation Conference 2016, 821-828, 2016 | 20 | 2016 |
| Smallify: Learning network size while training G Leclerc, M Vartak, RC Fernandez, T Kraska, S Madden arXiv preprint arXiv:1806.03723, 2018 | 16 | 2018 |
| Model metamers illuminate divergences between biological and artificial neural networks J Feather, G Leclerc, A Mądry, JH McDermott bioRxiv, 2022.05. 19.492678, 2022 | 8 | 2022 |
| Model metamers reveal divergent invariances between biological and artificial neural networks J Feather, G Leclerc, A Mądry, JH McDermott Nature Neuroscience 26 (11), 2017-2034, 2023 | 7 | 2023 |
| Madry, A. ffcv G Leclerc, A Ilyas, L Engstrom, SM Park, H Salman | 7 | 2022 |
| Rethinking backdoor attacks A Khaddaj, G Leclerc, A Makelov, K Georgiev, H Salman, A Ilyas, A Madry International Conference on Machine Learning, 16216-16236, 2023 | 3 | 2023 |
| Bayesian Skip Net: Building on Prior Information for the Prediction and Segmentation of Stroke Lesions J Klug, G Leclerc, E Dirren, MG Preti, D Van De Ville, E Carrera Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries …, 2021 | 2 | 2021 |
| Learning network size while training with ShrinkNets G Leclerc, RC Fernandez, S Madden Conference on Systems and Machine Learning, 2018 | 2 | 2018 |
| Revisiting Ensembles in an Adversarial Context: Improving Natural Accuracy A Saligrama, G Leclerc arXiv preprint arXiv:2002.11572, 2020 | 1 | 2020 |
| Extra Training Provides a Strong Baseline for CLIP A Khaddaj, H Salman, A Ilyas, G Leclerc, A Madry R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation …, 2023 | | 2023 |
| Your CLIP Model Might Be Undertrained A Khaddaj, H Salman, A Ilyas, G Leclerc, A Madry | | 2023 |
