 Squeezed Attention: Accelerating Long Context Length LLM InferenceAnnual Meeting of the Association for Computational Linguistics (ACL), 2024 |
 Fast Inference and Update of Probabilistic Density Estimation on
Trajectory PredictionIEEE International Conference on Computer Vision (ICCV), 2023 |
 Sub-quadratic Algorithms for Kernel Matrices via Kernel Density
EstimationInternational Conference on Learning Representations (ICLR), 2022 |
 Kernel approximation on algebraic varietiesSIAM Journal on applied algebra and geometry (SIAM J. Appl. Algebra Geom.), 2021 |
 Faster Kernel Matrix Algebra via Density EstimationInternational Conference on Machine Learning (ICML), 2021 |
 An Parallel Fast Direct Solver for Kernel MatricesIEEE International Parallel and Distributed Processing Symposium (IPDPS), 2017 |
 |
 ASKIT: Approximate Skeletonization Kernel-Independent Treecode in High
DimensionsSIAM Journal on Scientific Computing (SISC), 2014 |
 The Bregman Variational Dual-Tree FrameworkConference on Uncertainty in Artificial Intelligence (UAI), 2013 |
 Faster Gaussian Summation: Theory and ExperimentConference on Uncertainty in Artificial Intelligence (UAI), 2006 |
