| Domain adversarial neural networks for domain generalization: When it works and how to improve A Sicilia, X Zhao, SJ Hwang Machine Learning 112 (7), 2685-2721, 2023 | 75 | 2023 |
| Deephoops: Evaluating micro-actions in basketball using deep feature representations of spatio-temporal data A Sicilia, K Pelechrinis, K Goldsberry Proceedings of the 25th ACM SIGKDD international conference on knowledge …, 2019 | 46 | 2019 |
| Test-time fourier style calibration for domain generalization X Zhao, C Liu, A Sicilia, SJ Hwang, Y Fu arXiv preprint arXiv:2205.06427, 2022 | 30 | 2022 |
| Robust white matter hyperintensity segmentation on unseen domain X Zhao, A Sicilia, DS Minhas, EE O’Connor, HJ Aizenstein, WE Klunk, ... 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 1047-1051, 2021 | 17 | 2021 |
| The change that matters in discourse parsing: Estimating the impact of domain shift on parser error K Atwell, A Sicilia, SJ Hwang, M Alikhani arXiv preprint arXiv:2203.11317, 2022 | 16 | 2022 |
| Learning to generate equitable text in dialogue from biased training data A Sicilia, M Alikhani arXiv preprint arXiv:2307.04303, 2023 | 14 | 2023 |
| Pac-bayesian domain adaptation bounds for multiclass learners A Sicilia, K Atwell, M Alikhani, SJ Hwang Uncertainty in Artificial Intelligence, 1824-1834, 2022 | 9 | 2022 |
| Multi-domain learning by meta-learning: Taking optimal steps in multi-domain loss landscapes by inner-loop learning A Sicilia, X Zhao, DS Minhas, EE O’Connor, HJ Aizenstein, WE Klunk, ... 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI), 650-654, 2021 | 7 | 2021 |
| PittGrub: a frustration-free system to reduce food waste by notifying hungry college students M Silvis, A Sicilia, A Labrinidis Proceedings of the 24th ACM SIGKDD International Conference on Knowledge …, 2018 | 6 | 2018 |
| Deal, or no deal (or who knows)? forecasting uncertainty in conversations using large language models A Sicilia, H Kim, KR Chandu, M Alikhani, J Hessel arXiv preprint arXiv:2402.03284, 2024 | 5 | 2024 |
| Modeling non-cooperative dialogue: Theoretical and empirical insights A Sicilia, T Maidment, P Healy, M Alikhani Transactions of the Association for Computational Linguistics 10, 1084-1102, 2022 | 5 | 2022 |
| Pac bayesian performance guarantees for deep (stochastic) networks in medical imaging A Sicilia, X Zhao, A Sosnovskikh, SJ Hwang Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th …, 2021 | 5 | 2021 |
| LEATHER: A framework for learning to generate human-like text in dialogue A Sicilia, M Alikhani arXiv preprint arXiv:2210.07777, 2022 | 4 | 2022 |
| Isabel: An inclusive and collaborative task-oriented dialogue system A Sicilia, Y Asano, K Atwell, Q Cheng, D Gupta, S Hassan, M Inan, ... Alexa Prize TaskBot Challenge 2 Proceedings, 2023 | 3 | 2023 |
| Combining discourse coherence with large language models for more inclusive, equitable, and robust task-oriented dialogue K Atwell, M Inan, AB Sicilia, M Alikhani Proceedings of the 2024 Joint International Conference on Computational …, 2024 | 2 | 2024 |
| HumBEL: a human-in-the-loop approach for evaluating demographic factors of language models in human-machine conversations A Sicilia, JC Gates, M Alikhani arXiv preprint arXiv:2305.14195, 2023 | 2 | 2023 |
| An Active Learning Framework for Inclusive Generation by Large Language Models S Hassan, A Sicilia, M Alikhani arXiv preprint arXiv:2410.13641, 2024 | 1 | 2024 |
| Generating Signed Language Instructions in Large-Scale Dialogue Systems M Inan, K Atwell, A Sicilia, L Quandt, M Alikhani arXiv preprint arXiv:2410.14026, 2024 | 1 | 2024 |
| Active Learning for Robust and Representative LLM Generation in Safety-Critical Scenarios S Hassan, A Sicilia, M Alikhani arXiv preprint arXiv:2410.11114, 2024 | 1 | 2024 |
| Better Slow than Sorry: Introducing Positive Friction for Reliable Dialogue Systems M İnan, A Sicilia, S Dey, V Dongre, T Srinivasan, J Thomason, G Tür, ... arXiv preprint arXiv:2501.17348, 2025 | | 2025 |