{"total":63,"rows":[{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2308.16137","title":"LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models","created":"2023-08-30","cited_by_count":124,"area":null},{"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":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"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":"2501.12352","title":"Test-time regression: a unifying framework for designing sequence models with associative memory","created":"2025-01-21","cited_by_count":74,"area":null},{"id":"2302.02451","title":"KDEformer: Accelerating Transformers via Kernel Density Estimation","created":"2023-02-05","cited_by_count":58,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2404.03827","title":"Uniform Memory Retrieval with Larger Capacity for Modern Hopfield Models","created":"2024-04-04","cited_by_count":38,"area":null},{"id":"2501.15061","title":"PolaFormer: Polarity-aware Linear Attention for Vision Transformers","created":"2025-01-25","cited_by_count":32,"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":"2305.19798","title":"Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation","created":"2023-05-31","cited_by_count":29,"area":null},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2409.13265","title":"Towards LifeSpan Cognitive Systems","created":"2024-09-20","cited_by_count":13,"area":null},{"id":"2311.13541","title":"Linear Log-Normal Attention with Unbiased Concentration","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2411.07538","title":"Unraveling the Gradient Descent Dynamics of Transformers","created":"2024-11-12","cited_by_count":11,"area":null},{"id":"2210.07661","title":"CAB: Comprehensive Attention Benchmarking on Long Sequence Modeling","created":"2022-10-14","cited_by_count":10,"area":null},{"id":"2501.14577","title":"ZETA: Leveraging Z-order Curves for Efficient Top-k Attention","created":"2025-01-24","cited_by_count":9,"area":null},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2205.03720","title":"Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention","created":"2022-05-07","cited_by_count":6,"area":null},{"id":"2602.10056","title":"WildCat: Near-Linear Attention in Theory and Practice","created":"2026-02-10","cited_by_count":6,"area":null},{"id":"2112.05359","title":"Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences","created":"2021-12-10","cited_by_count":5,"area":null},{"id":"2206.00583","title":"Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks","created":"2022-06-01","cited_by_count":5,"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":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","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":"2503.10799","title":"Fixed-Point RNNs: Interpolating from Diagonal to Dense","created":"2025-03-13","cited_by_count":5,"area":"ssm"},{"id":"2503.20505","title":"Riemannian Optimization on Relaxed Indicator Matrix Manifold","created":"2025-03-26","cited_by_count":5,"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":"2409.12175","title":"Expanding Expressivity in Transformer Models with M\\\"obiusAttention","created":"2024-09-08","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":"2210.06741","title":"Why self-attention is Natural for Sequence-to-Sequence Problems? A Perspective from Symmetries","created":"2022-10-13","cited_by_count":3,"area":null},{"id":"2210.14469","title":"Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2306.15799","title":"FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2411.00151","title":"NIMBA: Towards Robust and Principled Processing of Point Clouds With SSMs","created":"2024-10-31","cited_by_count":3,"area":"ssm"},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2408.09650","title":"From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision","created":"2024-08-19","cited_by_count":2,"area":null},{"id":"2506.23551","title":"A unified framework for establishing the universal approximation of transformer-type architectures","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2505.12252","title":"SchoenbAt: Rethinking Attention with Polynomial basis","created":"2025-05-18","cited_by_count":1,"area":null},{"id":"2506.11043","title":"A Framework for Non-Linear Attention via Modern Hopfield Networks","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2606.27748","title":"Flexformer: Flexible Linear Transformer with Learnable Attention Kernel","created":"2026-06-26","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":"2310.14206","title":"Manifold-Preserving Transformers are Effective for Short-Long Range Encoding","created":"2023-10-22","cited_by_count":0,"area":null},{"id":"2411.03375","title":"Kernel Approximation using Analog In-Memory Computing","created":"2024-11-05","cited_by_count":0,"area":null},{"id":"2501.12896","title":"Irrational Complex Rotations Empower Low-bit Optimizers","created":"2025-01-22","cited_by_count":0,"area":null},{"id":"2502.00585","title":"Converting Transformers into DGNNs Form","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2504.17740","title":"Embedding Empirical Distributions for Computing Optimal Transport Maps","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2507.19041","title":"PGKET: A Photonic Gaussian Kernel Enhanced Transformer","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2509.10530","title":"Dynamic Adaptive Shared Experts with Grouped Multi-Head Attention Mixture of Experts","created":"2025-09-05","cited_by_count":0,"area":"moe"},{"id":"2510.01718","title":"Accelerating Attention with Basis Decomposition","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.16704","title":"Connecting Domains and Contrasting Samples: A Ladder for Domain Generalization","created":"2025-10-19","cited_by_count":0,"area":null},{"id":"2512.08061","title":"LUNA: Linear Universal Neural Attention with Generalization Guarantees","created":"2025-12-08","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":"2603.04127","title":"Data-Aware Random Feature Kernel for Transformers","created":"2026-03-04","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":"2607.23869","title":"A Coulomb Particle Model for Learning Kernel Attention in Transformers","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.11519","title":"FLARE++: Low-rank attention with dynamic attention routing","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2610.14219","title":"Learnable Low-Rank Polynomial Sketch for Effective Linear Attention","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}