Showing results 1 to 8 of 8
| Title | Author(s) | Issue Date | |
|---|---|---|---|
Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent Proceeding/Conference:The 28th International Conference on Artificial Intelligence and Statistics. (03/05/2025-05/05/2025, Mai Khao) | 3-May-2025 | ||
Curse of Attention: A Kernel-Based Perspective for Why Transformers Fail to Generalize on Time Series Forecasting and Beyond Proceeding/Conference:Conference on Parsimony and Learning 2025 (24/03/2025-27/03/2025, Stanford University, California) | 24-Mar-2025 | ||
Differential Privacy Mechanisms in Neural Tangent Kernel Regression Proceeding/Conference:IEEE/CVF Winter Conference on Applications of Computer Vision 2025 (28/02/2025-04/03/2025, Tucson, Arizona) | 28-Feb-2025 | ||
Fast John Ellipsoid Computation with Differential Privacy Optimization Proceeding/Conference:Conference on Parsimony and Learning 2025 (24/03/2025-27/03/2025, Stanford University, California) | 24-Mar-2025 | ||
Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs Proceeding/Conference:The 28th International Conference on Artificial Intelligence and Statistics. (03/05/2025-05/05/2025, Mai Khao) | 3-May-2025 | ||
HSR-Enhanced Sparse Attention Acceleration Proceeding/Conference:Conference on Parsimony and Learning 2025 (24/03/2025-27/03/2025, Stanford University, California) | 24-Mar-2025 | ||
Significance of the combination of inter-limb blood pressure differences in the elderly: The Northern Shanghai Study Journal:Journal of Clinical Hypertension | 2019 | ||
The Computational Limits of State-Space Models and Mamba via the Lens of Circuit Complexity Proceeding/Conference:Conference on Parsimony and Learning 2025 (24/03/2025-27/03/2025, Stanford University, California) | 24-Mar-2025 |