| 2025 | AISTATS | Provable Benefits of Task-Specific Prompts for In-context Learning. | Xiangyu Chang, Yingcong Li, Muti Kara, Samet Oymak, Amit Roy-Chowdhury |
| 2024 | AISTATS | Mechanics of Next Token Prediction with Self-Attention. | Yingcong Li, Yixiao Huang, Muhammed Emrullah Ildiz, Ankit Singh Rawat, Samet Oymak |
| 2024 | ICML | From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers. | Muhammed Emrullah Ildiz, Yixiao Huang, Yingcong Li, Ankit Singh Rawat, Samet Oymak |
| 2023 | AAAI | Provable Pathways: Learning Multiple Tasks over Multiple Paths. | Yingcong Li, Samet Oymak |
| 2023 | AAAI | Stochastic Contextual Bandits with Long Horizon Rewards. | Yuzhen Qin, Yingcong Li, Fabio Pasqualetti, Maryam Fazel, Samet Oymak |
| 2023 | ICASSP | On The Fairness of Multitask Representation Learning. | Yingcong Li, Samet Oymak |
| 2023 | ICML | Transformers as Algorithms: Generalization and Stability in In-context Learning. | Yingcong Li, Muhammed Emrullah Ildiz, Dimitris Papailiopoulos, Samet Oymak |
| 2021 | AAAI | Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks. | Xiangyu Chang, Yingcong Li, Samet Oymak, Christos Thrampoulidis |