{"total":15,"rows":[{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673,"area":null},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130,"area":null},{"id":"2203.16114","title":"A Fast Transformer-based General-Purpose Lossless Compressor","created":"2022-03-30","cited_by_count":26,"area":null},{"id":"2109.02377","title":"PermuteFormer: Efficient Relative Position Encoding for Long Sequences","created":"2021-09-06","cited_by_count":14,"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":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2603.16849","title":"GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators","created":"2026-03-17","cited_by_count":4,"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":"2305.10991","title":"Less is More! A slim architecture for optimal language translation","created":"2023-05-18","cited_by_count":0,"area":null},{"id":"2408.09158","title":"Linear Attention is Enough in Spatial-Temporal Forecasting","created":"2024-08-17","cited_by_count":0,"area":null},{"id":"2604.07239","title":"Efficient Learned Data Compression via Dual-Stream Feature Decoupling","created":"2026-04-08","cited_by_count":0,"area":null}],"next_cursor":null}