| Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models M Shu, W Nie, DA Huang, Z Yu, T Goldstein, A Anandkumar, C Xiao Conference on Neural Information Processing Systems (NeurIPS), 2022 | 147 | 2022 |
| On the reliability of watermarks for large language models J Kirchenbauer, J Geiping, Y Wen, M Shu, K Saifullah, K Kong, ... arXiv preprint arXiv:2306.04634, 2023 | 66 | 2023 |
| What do vision transformers learn? a visual exploration A Ghiasi, H Kazemi, E Borgnia, S Reich, M Shu, M Goldblum, AG Wilson, ... arXiv preprint arXiv:2212.06727, 2022 | 41 | 2022 |
| Gradient-Free Adversarial Training against Image Corruption for Learning-based Steering Y Shen, L Zheng, M Shu, W Li, T Goldstein, M Lin Conference on Neural Information Processing Systems (NeurIPS), 2021 | 36* | 2021 |
| Encoding Robustness to Image Style via Adversarial Feature Perturbation M Shu, Z Wu, M Goldblum, T Goldstein Conference on Neural Information Processing Systems (NeurIPS), 2021 | 28* | 2021 |
| On the exploitability of instruction tuning M Shu, J Wang, C Zhu, J Geiping, C Xiao, T Goldstein Advances in Neural Information Processing Systems 36, 2024 | 22 | 2024 |
| The Close Relationship Between Contrastive Learning and Meta-Learning R Ni, M Shu, H Souri, M Goldblum, T Goldstein International Conference on Learning Representations (ICLR), 2021 | 15 | 2021 |
| Bring your own data! self-supervised evaluation for large language models N Jain, K Saifullah, Y Wen, J Kirchenbauer, M Shu, A Saha, M Goldblum, ... arXiv preprint arXiv:2306.13651, 2023 | 13 | 2023 |
| Adversarial Differentiable Data Augmentation for Autonomous Systems M Shu, Y Shen, MC Lin, T Goldstein International Conference on Robotics and Automation (ICRA), 2021 | 11 | 2021 |
| Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability R Levin, M Shu, E Borgnia, F Huang, M Goldblum, T Goldstein Conference on Neural Information Processing Systems (NeurIPS), 2022, 2021 | 8 | 2021 |
| Battle of the backbones: A large-scale comparison of pretrained models across computer vision tasks M Goldblum, H Souri, R Ni, M Shu, V Prabhu, G Somepalli, ... Advances in Neural Information Processing Systems 36, 2024 | 7 | 2024 |
| Headless horseman: Adversarial attacks on transfer learning models A Abdelkader, MJ Curry, L Fowl, T Goldstein, A Schwarzschild, M Shu, ... ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020 | 6 | 2020 |
| Coercing LLMs to do and reveal (almost) anything J Geiping, A Stein, M Shu, K Saifullah, Y Wen, T Goldstein arXiv preprint arXiv:2402.14020, 2024 | 3 | 2024 |
| Towards accurate quantization and pruning via data-free knowledge transfer C Zhu, Z Xu, A Shafahi, M Shu, A Ghiasi, T Goldstein arXiv preprint arXiv:2010.07334, 2020 | 3 | 2020 |
| Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models Y Xu, J Yao, M Shu, Y Sun, Z Wu, N Yu, T Goldstein, F Huang arXiv preprint arXiv:2402.06659, 2024 | 2 | 2024 |
| Neural network prompt tuning A Anandkumar, C Xiao, W Nie, DA Huang, Z Yu, M Shu US Patent App. 18/243,348, 2024 | | 2024 |
| Model-Agnostic Hierarchical Attention for 3D Object Detection M Shu, L Xue, N Yu, R Martín-Martín, JC Niebles, C Xiong, R Xu arXiv preprint arXiv:2301.02650, 2023 | | 2023 |
Tom GoldsteinVolpi-Cupal Professor of Computer Science, University of MarylandVerified email at cs.umd.edu
