{"total":23,"rows":[{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2205.15317","title":"Chefs' Random Tables: Non-Trigonometric Random Features","created":"2022-05-30","cited_by_count":21,"area":null},{"id":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2305.00156","title":"Taming graph kernels with random features","created":"2023-04-29","cited_by_count":17,"area":null},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2201.02880","title":"Attention-based Random Forest and Contamination Model","created":"2022-01-08","cited_by_count":10,"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":"2311.12214","title":"Random Fourier Signature Features","created":"2023-11-20","cited_by_count":9,"area":null},{"id":"2511.17388","title":"Selective Rotary Position Embedding","created":"2025-11-21","cited_by_count":9,"area":null},{"id":"2410.03462","title":"Linear Transformer Topological Masking with Graph Random Features","created":"2024-10-04","cited_by_count":7,"area":null},{"id":"2504.10770","title":"Collaborative Bayesian Optimization via Wasserstein Barycenters","created":"2025-04-15","cited_by_count":7,"area":null},{"id":"2310.15494","title":"TRAMS: Training-free Memory Selection for Long-range Language Modeling","created":"2023-10-24","cited_by_count":5,"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":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"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":"2208.01191","title":"Implicit Two-Tower Policies","created":"2022-08-02","cited_by_count":3,"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":"2205.00534","title":"Generalized Reference Kernel for One-class Classification","created":"2022-05-01","cited_by_count":2,"area":null},{"id":"2602.03797","title":"Manifold Random Features","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2210.05168","title":"LARF: Two-level Attention-based Random Forests with a Mixture of Contamination Models","created":"2022-10-11","cited_by_count":0,"area":null}],"next_cursor":null}