| Deep batch active learning by diverse, uncertain gradient lower bounds JT Ash, C Zhang, A Krishnamurthy, J Langford, A Agarwal International Conference on Learning Representations, 2020 | 929 | 2020 |
| On warm-starting neural network training JT Ash, RP Adams Neural Information Processing Systems, 2020 | 235* | 2020 |
| Transformers learn shortcuts to automata B Liu, JT Ash, S Goel, A Krishnamurthy, C Zhang International Conference on Learning Representations, 2023 | 197 | 2023 |
| Learning deep resnet blocks sequentially using boosting theory F Huang, JT Ash, J Langford, R Schapire International Conference on Machine Learning, 2017 | 134 | 2017 |
| Understanding contrastive learning requires incorporating inductive biases N Saunshi, JT Ash, S Goel, D Misra, C Zhang, S Arora, S Kakade, ... International Conference on Machine Learning, 19250-19286, 2022 | 128 | 2022 |
| Gone Fishing: Neural Active Learning with Fisher Embeddings JT Ash, S Goel, A Krishnamurthy, S Kakade Neural Information Processing Systems, 2021 | 87 | 2021 |
| Joint analysis of gene expression levels and histological images identifies genes associated with tissue morphology JT Ash, G Darnell, D Munro, B Engelhardt Nature Communications, 458711, 2021 | 78 | 2021 |
| Automated particle picking for low-contrast macromolecules in cryo-electron microscopy R Langlois, J Pallesen, JT Ash, DN Ho, JL Rubinstein, J Frank Journal of structural biology 186 (1), 1-7, 2014 | 67 | 2014 |
| The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction P Sharma, JT Ash, D Misra International Conference on Learning Representations, 2024 | 59 | 2024 |
| Investigating the Role of Negatives in Contrastive Representation Learning JT Ash, S Goel, A Krishnamurthy, D Misra Artificial Intelligence and Statistics, 2022 | 55 | 2022 |
| A data-driven computational scheme for the nonlinear mechanical properties of cellular mechanical metamaterials under large deformation T Xue, A Beatson, M Chiaramonte, G Roeder, JT Ash, Y Menguc, ... Soft matter 16 (32), 7524-7534, 2020 | 54 | 2020 |
| Exposing Attention Glitches with Flip-Flop Language Modeling B Liu, JT Ash, S Goel, A Krishnamurthy, C Zhang Neural Information Processing Systems, 2023 | 50 | 2023 |
| End-to-end training of deep probabilistic CCA on paired biomedical observations G Gundersen, B Dumitrascu, JT Ash, BE Engelhardt Uncertainty in Artificial Intelligence, 2020 | 28 | 2020 |
| Learning Composable Energy Surrogates for PDE Order Reduction A Beatson, JT Ash, G Roeder, T Xie, RP Adams Neural Information Processing Systems, 2020 | 22 | 2020 |
| Streaming Active Learning with Deep Neural Networks A Saran, S Yousefi, A Krishnamurthy, J Langford, JT Ash International Conference On Machine Learning, 2023 | 20 | 2023 |
| An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models G Bhatt, Y Chen, AM Das, J Zhang, ST Truong, S Mussmann, Y Zhu, ... Association for Computational Linguistics, 2024 | 14 | 2024 |
| Anti-Concentrated Confidence Bonuses for Scalable Exploration JT Ash, C Zhang, S Goel, A Krishnamurthy, S Kakade International Conference on Learning Representations, 2022 | 12 | 2022 |
| Unsupervised domain adaptation using approximate label matching JT Ash, RE Schapire, BE Engelhardt ICML workshop on implicit generative models, 2017 | 9 | 2017 |
| Scratchable devices: user-friendly programming for household appliances J Ash, M Babes, G Cohen, S Jalal, S Lichtenberg, M Littman, V Marivate, ... Human-Computer Interaction. Towards Mobile and Intelligent Interaction …, 2011 | 8 | 2011 |
| Self-Improvement in Language Models: The Sharpening Mechanism A Huang, A Block, DJ Foster, D Rohatgi, C Zhang, M Simchowitz, JT Ash, ... arXiv preprint arXiv:2412.01951, 2024 | 3 | 2024 |
Akshay KrishnamurthyUniversity of Massachusetts AmherstVerified email at cs.umass.edu