{"total":213,"rows":[{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569,"area":null},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343,"area":null},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327,"area":null},{"id":"2111.13587","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","created":"2021-11-24","cited_by_count":248,"area":null},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2202.01381","title":"ETSformer: Exponential Smoothing Transformers for Time-series Forecasting","created":"2022-02-03","cited_by_count":148,"area":null},{"id":"2106.05667","title":"GraphiT: Encoding Graph Structure in Transformers","created":"2021-06-10","cited_by_count":147,"area":null},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128,"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":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2302.13214","title":"Fast Attention Requires Bounded Entries","created":"2023-02-26","cited_by_count":102,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2201.01032","title":"Learning Operators with Coupled Attention","created":"2022-01-04","cited_by_count":90,"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":"2402.09398","title":"Get More with LESS: Synthesizing Recurrence with KV Cache Compression for Efficient LLM Inference","created":"2024-02-14","cited_by_count":75,"area":"inference"},{"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":"2302.01170","title":"Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics","created":"2023-02-02","cited_by_count":66,"area":null},{"id":"2312.06528","title":"Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context","created":"2023-12-11","cited_by_count":63,"area":null},{"id":"2209.09236","title":"Real-time Online Video Detection with Temporal Smoothing Transformers","created":"2022-09-19","cited_by_count":58,"area":null},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51,"area":null},{"id":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"id":"2202.05798","title":"The Dual Form of Neural Networks Revisited: Connecting Test Time Predictions to Training Patterns via Spotlights of Attention","created":"2022-02-11","cited_by_count":46,"area":null},{"id":"2402.01258","title":"Transformers Learn Nonlinear Features In Context: Nonconvex Mean-field Dynamics on the Attention Landscape","created":"2024-02-02","cited_by_count":46,"area":null},{"id":"2406.06486","title":"Continuum Attention for Neural Operators","created":"2024-06-10","cited_by_count":40,"area":null},{"id":"2105.08399","title":"Relative Positional Encoding for Transformers with Linear Complexity","created":"2021-05-18","cited_by_count":37,"area":null},{"id":"2310.01655","title":"PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels","created":"2023-10-02","cited_by_count":36,"area":null},{"id":"2312.00751","title":"Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals","created":"2023-12-01","cited_by_count":32,"area":null},{"id":"2312.17044","title":"Length Extrapolation of Transformers: A Survey from the Perspective of Positional Encoding","created":"2023-12-28","cited_by_count":32,"area":null},{"id":"2405.05219","title":"Conv-Basis: A New Paradigm for Efficient Attention Inference and Gradient Computation in Transformers","created":"2024-05-08","cited_by_count":32,"area":null},{"id":"2501.06425","title":"Tensor Product Attention Is All You Need","created":"2025-01-11","cited_by_count":31,"area":null},{"id":"2202.09277","title":"(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering","created":"2022-02-18","cited_by_count":30,"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":"2110.08678","title":"Improving Transformers with Probabilistic Attention Keys","created":"2021-10-16","cited_by_count":28,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"area":null},{"id":"2411.05877","title":"Generative Adapter: Contextualizing Language Models in Parameters with A Single Forward Pass","created":"2024-11-08","cited_by_count":26,"area":null},{"id":"2501.02950","title":"Key-value memory in the brain","created":"2025-01-06","cited_by_count":24,"area":null},{"id":"2209.14105","title":"Exploring the Relationship between Architecture and Adversarially Robust Generalization","created":"2022-09-28","cited_by_count":23,"area":null},{"id":"2209.15190","title":"Neural Integral Equations","created":"2022-09-30","cited_by_count":23,"area":null},{"id":"2305.13571","title":"Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2308.13422","title":"QKSAN: A Quantum Kernel Self-Attention Network","created":"2023-08-25","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":"2402.11639","title":"In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness","created":"2024-02-18","cited_by_count":22,"area":null},{"id":"2406.06893","title":"Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot","created":"2024-06-11","cited_by_count":22,"area":null},{"id":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"area":null},{"id":"2303.02444","title":"Calibrating Transformers via Sparse Gaussian Processes","created":"2023-03-04","cited_by_count":21,"area":null},{"id":"2311.00519","title":"REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning","created":"2023-11-01","cited_by_count":21,"area":null},{"id":"2410.17770","title":"Small Singular Values Matter: A Random Matrix Analysis of Transformer Models","created":"2024-10-23","cited_by_count":21,"area":null},{"id":"2310.16076","title":"Practical Computational Power of Linear Transformers and Their Recurrent and Self-Referential Extensions","created":"2023-10-24","cited_by_count":20,"area":null},{"id":"2310.04861","title":"Uncovering hidden geometry in Transformers via disentangling position and context","created":"2023-10-07","cited_by_count":18,"area":null},{"id":"2312.10975","title":"Inducing Point Operator Transformer: A Flexible and Scalable Architecture for Solving PDEs","created":"2023-12-18","cited_by_count":18,"area":null},{"id":"2408.07307","title":"Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery","created":"2024-08-14","cited_by_count":18,"area":null},{"id":"2501.00658","title":"Understanding and Mitigating Bottlenecks of State Space Models through the Lens of Recency and Over-smoothing","created":"2024-12-31","cited_by_count":18,"area":"ssm"},{"id":"2505.11349","title":"Context parroting: A simple but tough-to-beat baseline for foundation models in scientific machine learning","created":"2025-05-16","cited_by_count":18,"area":null},{"id":"2112.08534","title":"Trading with the Momentum Transformer: An Intelligent and Interpretable Architecture","created":"2021-12-16","cited_by_count":16,"area":null},{"id":"2212.14852","title":"An Analysis of Attention via the Lens of Exchangeability and Latent Variable Models","created":"2022-12-30","cited_by_count":16,"area":null},{"id":"2403.19928","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15,"area":null},{"id":"2305.12086","title":"Prefix Propagation: Parameter-Efficient Tuning for Long Sequences","created":"2023-05-20","cited_by_count":15,"area":null},{"id":"2506.10959","title":"Understanding In-Context Learning on Structured Manifolds: Bridging Attention to Kernel Methods","created":"2025-06-12","cited_by_count":15,"area":null},{"id":"2502.12370","title":"Positional Encoding in Transformer-Based Time Series Models: A Survey","created":"2025-02-17","cited_by_count":14,"area":null},{"id":"2405.19162","title":"Does learning the right latent variables necessarily improve in-context learning?","created":"2024-05-29","cited_by_count":13,"area":null},{"id":"2408.04093","title":"Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters","created":"2024-08-07","cited_by_count":13,"area":null},{"id":"2210.05794","title":"Designing Robust Transformers using Robust Kernel Density Estimation","created":"2022-10-11","cited_by_count":11,"area":null},{"id":"2309.17257","title":"A Survey on Deep Learning Techniques for Action Anticipation","created":"2023-09-29","cited_by_count":11,"area":null},{"id":"2311.13541","title":"Linear Log-Normal Attention with Unbiased Concentration","created":"2023-11-22","cited_by_count":11,"area":null},{"id":"2502.00500","title":"Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation","created":"2025-02-01","cited_by_count":11,"area":"diffusion"},{"id":"2507.17657","title":"Attention (as Discrete-Time Markov) Chains","created":"2025-07-23","cited_by_count":11,"area":null},{"id":"2204.05424","title":"A Call for Clarity in Beam Search: How It Works and When It Stops","created":"2022-04-11","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":"2310.11984","title":"From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformers","created":"2023-10-18","cited_by_count":10,"area":null},{"id":"2406.14036","title":"Towards Infinite-Long Prefix in Transformer","created":"2024-06-20","cited_by_count":10,"area":null},{"id":"2408.03585","title":"Hierarchical Neural Constructive Solver for Real-world TSP Scenarios","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2502.20525","title":"Revisiting Kernel Attention with Correlated Gaussian Process Representation","created":"2025-02-27","cited_by_count":10,"area":null},{"id":"2207.03341","title":"Softmax-free Linear Transformers","created":"2022-07-05","cited_by_count":9,"area":null},{"id":"2505.11892","title":"Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transform","created":"2025-05-17","cited_by_count":9,"area":null},{"id":"2505.16983","title":"LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding","created":"2025-05-22","cited_by_count":9,"area":null},{"id":"2107.07089","title":"STAR: Sparse Transformer-based Action Recognition","created":"2021-07-15","cited_by_count":8,"area":null},{"id":"2312.06723","title":"Learning to See Low-Light Images via Feature Domain Adaptation","created":"2023-12-11","cited_by_count":8,"area":null},{"id":"2410.06746","title":"Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention","created":"2024-10-09","cited_by_count":8,"area":null},{"id":"2410.13779","title":"The Mystery of the Pathological Path-star Task for Language Models","created":"2024-10-17","cited_by_count":8,"area":null},{"id":"2106.01501","title":"Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins","created":"2021-06-02","cited_by_count":7,"area":null},{"id":"2309.01775","title":"Gated recurrent neural networks discover attention","created":"2023-09-04","cited_by_count":7,"area":null},{"id":"2309.09517","title":"FedGKD: Unleashing the Power of Collaboration in Federated Graph Neural Networks","created":"2023-09-18","cited_by_count":7,"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":"2406.13770","title":"Elliptical Attention","created":"2024-06-19","cited_by_count":7,"area":null},{"id":"2505.16284","title":"Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapse","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2112.01918","title":"Heuristic Search Planning with Deep Neural Networks using Imitation, Attention and Curriculum Learning","created":"2021-12-03","cited_by_count":6,"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":"2301.04020","title":"Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence","created":"2022-12-13","cited_by_count":6,"area":null},{"id":"2303.10232","title":"LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer","created":"2023-03-17","cited_by_count":6,"area":null},{"id":"2310.15719","title":"AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning","created":"2023-10-24","cited_by_count":6,"area":null},{"id":"2406.01460","title":"MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization","created":"2024-06-03","cited_by_count":6,"area":null},{"id":"2407.05489","title":"How Effective are State Space Models for Machine Translation?","created":"2024-07-07","cited_by_count":6,"area":"ssm"},{"id":"2410.12783","title":"Context-Scaling versus Task-Scaling in In-Context Learning","created":"2024-10-16","cited_by_count":6,"area":null},{"id":"2501.00659","title":"Why Are Positional Encodings Nonessential for Deep Autoregressive Transformers? Revisiting a Petroglyph","created":"2024-12-31","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":"2103.09857","title":"Value-aware Approximate Attention","created":"2021-03-17","cited_by_count":5,"area":null}],"next_cursor":"100"}