 When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?International Conference on Artificial Intelligence and Statistics (AISTATS), 2025 |
 Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient DescentInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2024 |
 Coupling without Communication and Drafter-Invariant Speculative DecodingInternational Symposium on Information Theory (ISIT), 2024 |
 The Closeness of In-Context Learning and Weight Shifting for Softmax
RegressionNeural Information Processing Systems (NeurIPS), 2023 |
