{"total":21,"rows":[{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2312.01990","title":"SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17,"area":null},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10,"area":null},{"id":"2301.13856","title":"Simplex Random Features","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2302.01128","title":"Mnemosyne: Learning to Train Transformers with Transformers","created":"2023-02-02","cited_by_count":9,"area":null},{"id":"2310.13225","title":"Scalable Neural Network Kernels","created":"2023-10-20","cited_by_count":9,"area":null},{"id":"2405.15310","title":"Spectraformer: A Unified Random Feature Framework for Transformer","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2302.00787","title":"FAVOR#: Sharp Attention Kernel Approximations via New Classes of Positive Random Features","created":"2023-02-01","cited_by_count":4,"area":null},{"id":"2311.01960","title":"Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products","created":"2023-11-03","cited_by_count":3,"area":null},{"id":"2401.03540","title":"SeTformer is What You Need for Vision and Language","created":"2024-01-07","cited_by_count":3,"area":null},{"id":"2410.10368","title":"Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphs","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2405.16541","title":"Variance-Reducing Couplings for Random Features","created":"2024-05-26","cited_by_count":2,"area":null},{"id":"2406.18802","title":"All Random Features Representations are Equivalent","created":"2024-06-27","cited_by_count":2,"area":null},{"id":"2601.22563","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2026-01-30","cited_by_count":2,"area":null},{"id":"2310.07370","title":"Orthogonal Random Features: Explicit Forms and Sharp Inequalities","created":"2023-10-11","cited_by_count":1,"area":null},{"id":"2602.03797","title":"Manifold Random Features","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2602.04915","title":"SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2209.06291","title":"Multiple View Performers for Shape Completion","created":"2022-09-13","cited_by_count":0,"area":null},{"id":"2410.09771","title":"EUGens: Efficient, Unified, and General Dense Layers","created":"2024-10-13","cited_by_count":0,"area":null},{"id":"2610.13568","title":"Rationally Linearized MLPs","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}