Understanding catastrophic forgetting in language models via implicit inference S Kotha, JM Springer, A Raghunathan arXiv preprint arXiv:2309.10105, 2023 | 15 | 2023 |
Repetition Improves Language Model Embeddings JM Springer, S Kotha, D Fried, G Neubig, A Raghunathan arXiv preprint arXiv:2402.15449, 2024 | 4 | 2024 |
Provably Bounding Neural Network Preimages S Kotha, C Brix, Z Kolter, K Dvijotham, H Zhang Advances in Neural Information Processing Systems 36, 2023 | 3 | 2023 |
A safe harbor for ai evaluation and red teaming S Longpre, S Kapoor, K Klyman, A Ramaswami, R Bommasani, ... arXiv preprint arXiv:2403.04893, 2024 | 2 | 2024 |
Machine-Based Spectral Classification of Weak CN & Carbon Stars in M31 S Kotha, R Raikar, P GuhaThakurta, A Bhattacharya, A Chang Bulletin of the American Physical Society 64, 2019 | 1 | 2019 |
Jailbreaking is Best Solved by Definition T Kim, S Kotha, A Raghunathan arXiv preprint arXiv:2403.14725, 2024 | | 2024 |
CELESTIAL: Classification Enabled via Labelless Embeddings with Self-supervised Telescope Image Analysis Learning S Kotha, A Koul, S Ganju, M Kasam arXiv preprint arXiv:2201.08001, 2022 | | 2022 |
SpaceML Worldview Search-Learnings from an AI citizen scientist team building a NoCode Data Curator from Unlabeled Petabyte Scale Imagery A Koul, A Krishnan, T Narayanan, R Venguswamy, S Muthukrishnan, ... AGU Fall Meeting Abstracts 2021, IN11B-06, 2021 | | 2021 |