| A watermark for large language models J Kirchenbauer, J Geiping, Y Wen, J Katz, I Miers, T Goldstein International Conference on Machine Learning, 17061-17084, 2023 | 730 | 2023 |
| 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 | 370* | 2023 |
| Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery Y Wen, N Jain, J Kirchenbauer, M Goldblum, J Geiping, T Goldstein Advances in Neural Information Processing Systems 36, 51008-51025, 2023 | 259 | 2023 |
| 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 | 185* | 2023 |
| Tree-ring watermarks: Fingerprints for diffusion images that are invisible and robust Y Wen, J Kirchenbauer, J Geiping, T Goldstein arXiv preprint arXiv:2305.20030, 2023 | 170* | 2023 |
| Neftune: Noisy embeddings improve instruction finetuning N Jain, P Chiang, Y Wen, J Kirchenbauer, HM Chu, G Somepalli, ... International Conference on Learning Representations (ICLR) 2024, 2024 | 86* | 2024 |
| GOAT: A global transformer on large-scale graphs K Kong, J Chen, J Kirchenbauer, R Ni, CB Bruss, T Goldstein International Conference on Machine Learning, 17375-17390, 2023 | 64 | 2023 |
| Bring Your Own Data! Self-Sensitivity Evaluation for Large Language Models N Jain, K Saifullah, Y Wen, J Kirchenbauer, M Shu, A Saha, M Goldblum, ... First Conference on Language Modeling, 0 | 24* | |
| A closer look at distribution shifts and out-of-distribution generalization on graphs M Ding, K Kong, J Chen, J Kirchenbauer, M Goldblum, D Wipf, F Huang, ... | 22 | 2021 |
| Transformers can do arithmetic with the right embeddings S McLeish, A Bansal, A Stein, N Jain, J Kirchenbauer, B Bartoldson, ... Advances in Neural Information Processing Systems 37, 108012-108041, 2024 | 21* | 2024 |
| Be like a goldfish, don't memorize! mitigating memorization in generative llms A Hans, J Kirchenbauer, Y Wen, N Jain, H Kazemi, P Singhania, S Singh, ... Advances in Neural Information Processing Systems 37, 24022-24045, 2024 | 19 | 2024 |
| Genqa: Generating millions of instructions from a handful of prompts J Chen, R Qadri, Y Wen, N Jain, J Kirchenbauer, T Zhou, T Goldstein arXiv preprint arXiv:2406.10323, 2024 | 13 | 2024 |
| Lmd3: Language model data density dependence J Kirchenbauer, G Honke, G Somepalli, J Geiping, D Ippolito, K Lee, ... arXiv preprint arXiv:2405.06331, 2024 | 8 | 2024 |
| Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach J Geiping, S McLeish, N Jain, J Kirchenbauer, S Singh, BR Bartoldson, ... arXiv preprint arXiv:2502.05171, 2025 | 7 | 2025 |
| Optune: Efficient online preference tuning L Chen, J Chen, C Liu, J Kirchenbauer, D Soselia, C Zhu, T Goldstein, ... arXiv preprint arXiv:2406.07657, 2024 | 3 | 2024 |
| What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability J Kirchenbauer, J Oaks, E Heim | 3 | 2022 |
| How to do a vocab swap? a study of embedding replacement for pre-trained transformers N Jain, J Kirchenbauer, J Geiping, T Goldstein | 2 | 2022 |
| Democratizing AI: Open-source Scalable LLM Training on GPU-based Supercomputers S Singh, P Singhania, A Ranjan, J Kirchenbauer, J Geiping, Y Wen, ... SC24: International Conference for High Performance Computing, Networking …, 2024 | 1 | 2024 |
| When Can You Get Away with Low Memory Adam? DS Kalra, J Kirchenbauer, M Barkeshli, T Goldstein arXiv preprint arXiv:2503.01843, 2025 | | 2025 |
| Exploiting Sparsity for Long Context Inference: Million Token Contexts on Commodity GPUs R Synk, M Hoover, J Kirchenbauer, N Jain, A Stein, M Shu, JM Sanchez, ... arXiv preprint arXiv:2502.06766, 2025 | | 2025 |
Tom GoldsteinVolpi-Cupal Professor of Computer Science, University of MarylandVerified email at cs.umd.edu
