| FRAPPÉ: A Group Fairness Framework for Post-Processing Everything A Ţifrea, P Lahoti, B Packer, Y Halpern, A Beirami, F Prost Forty-first International Conference on Machine Learning (ICML), 2024 | | 2024 |
| Controlled Decoding from Language Models S Mudgal*, J Lee*, H Ganapathy, YG Li, T Wang, Y Huang, Z Chen, ... Forty-first International Conference on Machine Learning (ICML), 2024 | 7 | 2024 |
| Asymptotics of Language Model Alignment JQ Yang, S Salamatian, Z Sun, AT Suresh, A Beirami International Symposium on Information Theory (ISIT), 2024 | | 2024 |
| Enhancing Group Fairness in Online Settings Using Oblique Decision Forests SBR Chowdhury, N Monath, A Beirami, R Kidambi, A Dubey, A Ahmed, ... 12th International Conference on Learning Representations (ICLR) Spotlight, 2024 | | 2024 |
| Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective B Puranik, A Beirami, Y Qin, U Madhow International Conference on Artificial Intelligence and Statistics (AISTATS), 2024 | | 2024 |
| Reuse Your Rewards: Reward Model Transfer for Zero-Shot Cross-Lingual Alignment Z Wu, A Balashankar, Y Kim, J Eisenstein, A Beirami arXiv preprint arXiv:2404.12318, 2024 | | 2024 |
| Multi-Group Fairness Evaluation via Conditional Value-at-Risk Testing LM Paes, AT Suresh, A Beutel, FP Calmon, A Beirami IEEE Journal on Selected Areas in Information Theory (JSAIT), 2024 | | 2024 |
| Optimal Block-Level Draft Verification for Accelerating Speculative Decoding Z Sun, JH Ro, A Beirami, AT Suresh arXiv preprint arXiv:2403.10444, 2024 | | 2024 |
| Gradient-Based Language Model Red Teaming N Wichers, C Denison, A Beirami 18th Conf of European Chapter of the Assoc for Computational Linguistics (EACL), 2024 | 2 | 2024 |
| Break it, Imitate it, Fix it: Robustness by Generating Human-Like Attacks A Sinha*, A Balashankar*, A Beirami, T Avrahami, J Chen, A Beutel Transactions on Machine Learning Research (TMLR), 2024 | | 2024 |
| Theoretical guarantees on the best-of-n alignment policy A Beirami, A Agarwal, J Berant, A D'Amour, J Eisenstein, C Nagpal, ... arXiv preprint arXiv:2401.01879, 2024 | 2 | 2024 |
| SpecTr++: Improved transport plans for speculative decoding of large language models K Ahn, A Beirami, Z Sun, AT Suresh NeurIPS 2023 Workshop Optimal Transport and Machine Learning, 2023 | | 2023 |
| Helping or herding? reward model ensembles mitigate but do not eliminate reward hacking J Eisenstein, C Nagpal, A Agarwal, A Beirami, A D'Amour, DJ Dvijotham, ... arXiv preprint arXiv:2312.09244, 2023 | 10 | 2023 |
| Improving Diversity of Demographic Representation in Large Language Models via Collective-Critiques and Self-Voting P Lahoti, N Blumm, X Ma, R Kotikalapudi, S Potluri, Q Tan, H Srinivasan, ... Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023 | 5 | 2023 |
| SpecTr: Fast speculative decoding via optimal transport Z Sun*, AT Suresh*, JH Ro, A Beirami, H Jain, F Yu 37th Conference on Neural Information Processing Systems (NeurIPS), 2023 | 20 | 2023 |
| Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts P Sarkar, A Beirami, A Etemad 37th Conference on Neural Information Processing Systems (NeurIPS) Spotlight, 2023 | 2 | 2023 |
| Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning A Balashankar, X Ma, A Sinha, A Beirami, Y Qin, J Chen, A Beutel arXiv preprint arXiv:2310.16959, 2023 | | 2023 |
| A systematic survey of prompt engineering on vision-language foundation models J Gu, Z Han, S Chen, A Beirami, B He, G Zhang, R Liao, Y Qin, V Tresp, ... arXiv preprint arXiv:2307.12980, 2023 | 43 | 2023 |
| Towards A Scalable Solution for Improving Multi-Group Fairness in Compositional Classification J Atwood, T Tian, B Packer, M Deodhar, J Chen, A Beutel, F Prost, ... International Conference on Machine Learning (ICML) Workshops, 2023 | | 2023 |
| Let's Do a Thought Experiment: Using Counterfactuals to Improve Moral Reasoning X Ma, S Mishra, A Beirami, A Beutel, J Chen International Conference on Machine Learning (ICML) Workshops, 2023 | 5 | 2023 |
Faramarz FekriGeorgia TechVerified email at ece.gatech.edu
