| Transformers as Algorithms: Generalization and Stability in In-context Learning Y Li, ME Ildiz, D Papailiopoulos, S Oymak International Conference on Machine Learning, 2023 | 110* | 2023 |
| Provable benefits of overparameterization in model compression: From double descent to pruning neural networks X Chang, Y Li, S Oymak, C Thrampoulidis Proceedings of the AAAI Conference on Artificial Intelligence 35 (8), 6974-6983, 2021 | 54 | 2021 |
| Visualize your IP-over-optical network in realtime: A P4-based flexible multilayer in-band network telemetry (ML-INT) system B Niu, J Kong, S Tang, Y Li, Z Zhu IEEE Access 7, 82413-82423, 2019 | 48 | 2019 |
| Transformers as support vector machines DA Tarzanagh, Y Li, C Thrampoulidis, S Oymak arXiv preprint arXiv:2308.16898, 2023 | 47 | 2023 |
| Max-margin token selection in attention mechanism DA Tarzanagh, Y Li, X Zhang, S Oymak Thirty-seventh Conference on Neural Information Processing Systems, 2023 | 29* | 2023 |
| Dissecting Chain-of-Thought: A Study on Compositional In-Context Learning of MLPs Y Li, K Sreenivasan, A Giannou, D Papailiopoulos, S Oymak Thirty-seventh Conference on Neural Information Processing Systems, 2023 | 23* | 2023 |
| Mechanics of next token prediction with self-attention Y Li, Y Huang, ME Ildiz, AS Rawat, S Oymak International Conference on Artificial Intelligence and Statistics, 685-693, 2024 | 11 | 2024 |
| Provable and efficient continual representation learning Y Li, M Li, MS Asif, S Oymak arXiv preprint arXiv:2203.02026, 2022 | 8 | 2022 |
| From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers ME Ildiz, Y Huang, Y Li, AS Rawat, S Oymak arXiv preprint arXiv:2402.13512, 2024 | 4 | 2024 |
| Provable pathways: Learning multiple tasks over multiple paths Y Li, S Oymak The Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023 | 4 | 2023 |
| Network nervous system: When multilayer telemetry meets AI-assisted service provisioning J Kong, B Niu, S Tang, Y Li, H Fang, W Lu, Z Zhu 2019 18th International Conference on Optical Communications and Networks …, 2019 | 4 | 2019 |
| Stochastic contextual bandits with long horizon rewards Y Qin, Y Li, F Pasqualetti, M Fazel, S Oymak The Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023 | 3 | 2023 |
| Leveraging multilayer telemetry to realize AI-assisted service provisioning in IP over elastic optical networks Z Zhu, B Niu, J Kong, S Tang, Y Li, H Fang, W Lu 2019 24th OptoElectronics and Communications Conference (OECC) and 2019 …, 2019 | 2 | 2019 |
| On the fairness of multitask representation learning Y Li, S Oymak ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 1 | 2023 |
