| SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training G Somepalli, M Goldblum, A Schwarzschild, CB Bruss, T Goldstein NeurIPS 2022 Tabular Representation Learning Workshop, 2022 | 374* | 2022 |
| Baseline defenses for adversarial attacks against aligned language models N Jain, A Schwarzschild, Y Wen, G Somepalli, J Kirchenbauer, P Chiang, ... arXiv preprint arXiv:2309.00614, 2023 | 309* | 2023 |
| Diffusion art or digital forgery? investigating data replication in diffusion models G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 304 | 2023 |
| Understanding and Mitigating Copying in Diffusion Models G Somepalli, V Singla, M Goldblum, J Geiping, T Goldstein Advances in Neural Information Processing Systems 36, 2023 | 103 | 2023 |
| What doesn't kill you makes you robust (er): How to adversarially train against data poisoning J Geiping, L Fowl, G Somepalli, M Goldblum, M Moeller, T Goldstein arXiv preprint arXiv:2102.13624, 2021 | 85 | 2021 |
| Neftune: Noisy embeddings improve instruction finetuning N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ... arXiv preprint arXiv:2310.05914, 2023 | 78* | 2023 |
| Can neural nets learn the same model twice? investigating reproducibility and double descent from the decision boundary perspective G Somepalli, L Fowl, A Bansal, P Yeh-Chiang, Y Dar, R Baraniuk, ... Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 75 | 2022 |
| 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 | 62 | 2024 |
| How much data are augmentations worth? An investigation into scaling laws, invariance, and implicit regularization J Geiping, M Goldblum, G Somepalli, R Shwartz-Ziv, T Goldstein, ... ICLR 2023, 2022 | 36 | 2022 |
| Cinepile: A long video question answering dataset and benchmark R Rawal, K Saifullah, M Farré, R Basri, D Jacobs, G Somepalli, ... arXiv preprint arXiv:2405.08813, 2024 | 22 | 2024 |
| Measuring Style Similarity in Diffusion Models G Somepalli, A Gupta, K Gupta, S Palta, M Goldblum, J Geiping, ... European Conference on Computer Vision, 2025, 2024 | 18 | 2024 |
| Unsupervised Anomaly Detection with Adversarial Mirrored AutoEncoders G Somepalli, Y Wu, Y Balaji, B Vinzamuri, S Feizi Uncertainty in Artificial Intelligence, PMLR 161:365-375, 2021 | 18* | 2021 |
| From Pixels to Prose: A Large Dataset of Dense Image Captions V Singla, K Yue, S Paul, R Shirkavand, M Jayawardhana, A Ganjdanesh, ... arXiv preprint arXiv:2406.10328, 2024 | 14 | 2024 |
| A performance-driven benchmark for feature selection in tabular deep learning V Cherepanova, R Levin, G Somepalli, J Geiping, CB Bruss, AG Wilson, ... Advances in Neural Information Processing Systems 36, 41956-41979, 2023 | 14 | 2023 |
| Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs A Hans, Y Wen, N Jain, J Kirchenbauer, H Kazemi, P Singhania, S Singh, ... arXiv preprint arXiv:2406.10209, 2024 | 10* | 2024 |
| Prioritizing and characterizing functionally relevant genes across human tissues G Somepalli, S Sahoo, A Singh, S Hannenhalli PLoS Computational Biology 17 (7), e1009194, 2021 | 9 | 2021 |
| LMD3: Language Model Data Density Dependence J Kirchenbauer, G Honke, G Somepalli, J Geiping, D Ippolito, K Lee, ... arXiv preprint arXiv:2405.06331, 2024 | 6 | 2024 |
| Patchgame: Learning to signal mid-level patches in referential games K Gupta, G Somepalli, A Anubhav, VYJ Magalle Hewa, M Zwicker, ... Advances in Neural Information Processing Systems 34, 26015-26027, 2021 | 6 | 2021 |
| Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Models R Shirkavand, P Yu, S Gao, G Somepalli, T Goldstein, H Huang arXiv preprint arXiv:2412.15341, 2024 | | 2024 |
| CALVIN: Improved Contextual Video Captioning via Instruction Tuning G Somepalli, A Chowdhury, J Geiping, R Basri, T Goldstein, DW Jacobs The Thirty-eighth Annual Conference on Neural Information Processing Systems, 0 | | |
Tom GoldsteinVolpi-Cupal Professor of Computer Science, University of MarylandVerified email at cs.umd.edu
