Understanding adversarial training: Increasing local stability of supervised models through robust optimization U Shaham, Y Yamada, S Negahban Neurocomputing 307, 195-204, 2018 | 533 | 2018 |
Feature selection using stochastic gates Y Yamada, O Lindenbaum, S Negahban, Y Kluger International conference on machine learning, 10648-10659, 2020 | 151 | 2020 |
Can wikipedia help offline reinforcement learning? M Reid, Y Yamada, SS Gu arXiv preprint arXiv:2201.12122, 2022 | 93 | 2022 |
Defending against adversarial images using basis functions transformations U Shaham, J Garritano, Y Yamada, E Weinberger, A Cloninger, X Cheng, ... arXiv preprint arXiv:1803.10840, 2018 | 75 | 2018 |
Evaluating gpt-4 and chatgpt on japanese medical licensing examinations J Kasai, Y Kasai, K Sakaguchi, Y Yamada, D Radev arXiv preprint arXiv:2303.18027, 2023 | 59 | 2023 |
Does robustness on imagenet transfer to downstream tasks? Y Yamada, M Otani Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2022 | 30 | 2022 |
When are Lemons Purple? The Concept Association Bias of Vision-Language Models Y Yamada, Y Tang, Y Zhang, I Yildirim Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023 | 24* | 2023 |
Support recovery with Projected Stochastic Gates: Theory and application for linear models S Jana, H Li, Y Yamada, O Lindenbaum Signal Processing 213, 109193, 2023 | 11* | 2023 |
Evaluating Spatial Understanding of Large Language Models Y Yamada, Y Bao, AK Lampinen, J Kasai, I Yildirim Transactions on Machine Learning Research (TMLR), 2024 | 9 | 2024 |
L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects Y Yamada, K Chandu, Y Lin, J Hessel, I Yildirim, Y Choi arXiv preprint arXiv:2402.09052, 2024 | 1 | 2024 |
Three-Dimensional Reconstruction Pre-Training as a Prior to Improve Robustness to Adversarial Attacks and Spurious Correlation Y Yamada, FW Zhang, Y Kluger, I Yildirim Entropy 26 (3), 258, 2024 | | 2024 |
Transferability of ImageNet Robustness to Downstream Tasks Y Yamada, M Otani | | |
Exploiting 3D Shape Bias towards Robust Vision Y Yamada, Y Kluger, S Negahban, I Yildirim SVRHM 2021 Workshop@ NeurIPS, 0 | | |