{"total":25,"rows":[{"id":"2210.10890","title":"Mitigating spectral bias for the multiscale operator learning","created":"2022-10-19","cited_by_count":44,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2212.08136","title":"Efficient Long Sequence Modeling via State Space Augmented Transformer","created":"2022-12-15","cited_by_count":37,"area":null},{"id":"2204.04667","title":"Linear Complexity Randomized Self-attention Mechanism","created":"2022-04-10","cited_by_count":31,"area":null},{"id":"2204.13154","title":"Attention Mechanism in Neural Networks: Where it Comes and Where it Goes","created":"2022-04-27","cited_by_count":29,"area":null},{"id":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2209.14977","title":"Transformer Meets Boundary Value Inverse Problems","created":"2022-09-29","cited_by_count":22,"area":null},{"id":"2405.16325","title":"SLoPe: Double-Pruned Sparse Plus Lazy Low-Rank Adapter Pretraining of LLMs","created":"2024-05-25","cited_by_count":20,"area":null},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2203.01178","title":"DCT-Former: Efficient Self-Attention with Discrete Cosine Transform","created":"2022-03-02","cited_by_count":12,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"area":null},{"id":"2406.13762","title":"Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2209.12816","title":"Fast-FNet: Accelerating Transformer Encoder Models via Efficient Fourier Layers","created":"2022-09-26","cited_by_count":5,"area":null},{"id":"2406.08128","title":"Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2507.02748","title":"Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics","created":"2025-07-03","cited_by_count":5,"area":null},{"id":"2208.00579","title":"Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization","created":"2022-08-01","cited_by_count":4,"area":null},{"id":"2211.16368","title":"DBA: Efficient Transformer with Dynamic Bilinear Low-Rank Attention","created":"2022-11-24","cited_by_count":4,"area":null},{"id":"2503.00687","title":"Transformer Meets Twicing: Harnessing Unattended Residual Information","created":"2025-03-02","cited_by_count":3,"area":null},{"id":"2408.08567","title":"S$^3$Attention: Improving Long Sequence Attention with Smoothed Skeleton Sketching","created":"2024-08-16","cited_by_count":2,"area":null},{"id":"2503.10632","title":"Kolmogorov-Arnold Attention: Is Learnable Attention Better For Vision Transformers?","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2510.21956","title":"Transformer Based Linear Attention with Optimized GPU Kernel Implementation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2606.27372","title":"DnA: Denoising Attention for Visual Tasks","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.13241","title":"EMAGN: Efficient Multi-Attention Graph Network via Learned Clustering for Scalable Traffic Forecasting","created":"2026-07-14","cited_by_count":0,"area":null}],"next_cursor":null}