{"total":51,"rows":[{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"area":null},{"id":"2205.09921","title":"KERPLE: Kernelized Relative Positional Embedding for Length Extrapolation","created":"2022-05-20","cited_by_count":86,"area":null},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2402.18510","title":"RNNs are not Transformers (Yet): The Key Bottleneck on In-context Retrieval","created":"2024-02-28","cited_by_count":64,"area":null},{"id":"2205.13401","title":"Your Transformer May Not be as Powerful as You Expect","created":"2022-05-26","cited_by_count":55,"area":null},{"id":"2107.07999","title":"From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers","created":"2021-07-16","cited_by_count":38,"area":null},{"id":"2405.14722","title":"DAPE: Data-Adaptive Positional Encoding for Length Extrapolation","created":"2024-05-23","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":"2110.04367","title":"Hybrid Random Features","created":"2021-10-08","cited_by_count":25,"area":null},{"id":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2307.14010","title":"ESSAformer: Efficient Transformer for Hyperspectral Image Super-resolution","created":"2023-07-26","cited_by_count":23,"area":null},{"id":"2402.13934","title":"Do Efficient Transformers Really Save Computation?","created":"2024-02-21","cited_by_count":20,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2402.12535","title":"Locality-Sensitive Hashing-Based Efficient Point Transformer with Applications in High-Energy Physics","created":"2024-02-19","cited_by_count":12,"area":null},{"id":"2203.02588","title":"A Quality Index Metric and Method for Online Self-Assessment of Autonomous Vehicles Sensory Perception","created":"2022-03-04","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":"2407.03157","title":"Let the Code LLM Edit Itself When You Edit the Code","created":"2024-07-03","cited_by_count":10,"area":"inference"},{"id":"2410.04798","title":"DAPE V2: Process Attention Score as Feature Map for Length Extrapolation","created":"2024-10-07","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":"2305.20019","title":"Monotonic Location Attention for Length Generalization","created":"2023-05-31","cited_by_count":9,"area":null},{"id":"2302.03038","title":"Single Cells Are Spatial Tokens: Transformers for Spatial Transcriptomic Data Imputation","created":"2023-02-06","cited_by_count":7,"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":"2509.21936","title":"Statistical Advantage of Softmax Attention: Insights from Single-Location Regression","created":"2025-09-26","cited_by_count":7,"area":null},{"id":"2202.00710","title":"Improving Sample Efficiency of Value Based Models Using Attention and Vision Transformers","created":"2022-02-01","cited_by_count":4,"area":null},{"id":"2210.04417","title":"Self-explaining Hierarchical Model for Intraoperative Time Series","created":"2022-10-10","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":"2308.11185","title":"MEGA: Multimodal Alignment Aggregation and Distillation For Cinematic Video Segmentation","created":"2023-08-22","cited_by_count":4,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2509.23436","title":"LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport","created":"2025-09-27","cited_by_count":4,"area":null},{"id":"2406.15881","title":"Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers","created":"2024-06-22","cited_by_count":3,"area":null},{"id":"2110.02453","title":"Ripple Attention for Visual Perception with Sub-quadratic Complexity","created":"2021-10-06","cited_by_count":2,"area":null},{"id":"2406.16450","title":"Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers","created":"2024-06-24","cited_by_count":2,"area":null},{"id":"2507.03340","title":"Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency","created":"2025-07-04","cited_by_count":2,"area":null},{"id":"2603.18761","title":"NeuroGame Transformer: Gibbs-Inspired Attention Driven by Game Theory and Statistical Physics","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2202.11364","title":"FastRPB: a Scalable Relative Positional Encoding for Long Sequence Tasks","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2211.16289","title":"Lightweight Structure-Aware Attention for Visual Understanding","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2410.14183","title":"In-context Learning for Mixture of Linear Regressions: Existence, Generalization and Training Dynamics","created":"2024-10-18","cited_by_count":1,"area":null},{"id":"2512.12805","title":"From Small to Large: Generalization Bounds for Transformers on Variable-Size Inputs","created":"2025-12-14","cited_by_count":1,"area":null},{"id":"2605.10706","title":"RelFlexformer: Efficient Attention 3D-Transformers for Integrable Relative Positional Encodings","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2609.36062","title":"SMat-Attention: Structured Long-Context Sequence Modeling","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2302.02224","title":"TAP: The Attention Patch for Cross-Modal Knowledge Transfer from Unlabeled Modality","created":"2023-02-04","cited_by_count":0,"area":null},{"id":"2305.09028","title":"SKI to go Faster: Accelerating Toeplitz Neural Networks via Asymmetric Kernels","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2602.12851","title":"Chimera: Neuro-Symbolic Attention Primitives for Trustworthy Dataplane Intelligence","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.02144","title":"Projection-Free Transformers via Gaussian Kernel Attention","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.29983","title":"Improving Adversarial Robustness of Attribution via Implicit Regularization","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.23869","title":"A Coulomb Particle Model for Learning Kernel Attention in Transformers","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2607.26369","title":"ClockRoPE: Random Fourier Rotations for Temporal Routine Modeling","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}