{"total":89,"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":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400,"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":"2111.05464","title":"Are Transformers More Robust Than CNNs?","created":"2021-11-10","cited_by_count":187,"area":null},{"id":"2204.12451","title":"Understanding The Robustness in Vision Transformers","created":"2022-04-26","cited_by_count":144,"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":"2310.03025","title":"Retrieval meets Long Context Large Language Models","created":"2023-10-04","cited_by_count":115,"area":null},{"id":"2402.15627","title":"MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs","created":"2024-02-23","cited_by_count":112,"area":null},{"id":"2110.13711","title":"Hierarchical Transformers Are More Efficient Language Models","created":"2021-10-26","cited_by_count":102,"area":null},{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2107.08391","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","created":"2021-07-18","cited_by_count":101,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77,"area":null},{"id":"2209.00638","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","created":"2022-09-01","cited_by_count":55,"area":null},{"id":"2305.12095","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","created":"2023-05-20","cited_by_count":55,"area":null},{"id":"2301.03044","title":"A Survey on Transformers in Reinforcement Learning","created":"2023-01-08","cited_by_count":50,"area":null},{"id":"2210.10349","title":"Museformer: Transformer with Fine- and Coarse-Grained Attention for Music Generation","created":"2022-10-19","cited_by_count":49,"area":null},{"id":"2109.12218","title":"Long-Range Transformers for Dynamic Spatiotemporal Forecasting","created":"2021-09-24","cited_by_count":46,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2210.09573","title":"ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design","created":"2022-10-18","cited_by_count":41,"area":null},{"id":"2107.06419","title":"FLAT: An Optimized Dataflow for Mitigating Attention Bottlenecks","created":"2021-07-13","cited_by_count":39,"area":null},{"id":"2303.11607","title":"Transformers in Speech Processing: A Survey","created":"2023-03-21","cited_by_count":39,"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":"2311.05908","title":"FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores","created":"2023-11-10","cited_by_count":33,"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":"2211.10526","title":"Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference","created":"2022-11-18","cited_by_count":28,"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":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null},{"id":"2112.07210","title":"Simple Local Attentions Remain Competitive for Long-Context Tasks","created":"2021-12-14","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":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2305.15099","title":"Fourier Transformer: Fast Long Range Modeling by Removing Sequence Redundancy with FFT Operator","created":"2023-05-24","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":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2205.14794","title":"Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning","created":"2022-05-30","cited_by_count":13,"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":"2501.03006","title":"TransPixeler: Advancing Text-to-Video Generation with Transparency","created":"2025-01-06","cited_by_count":12,"area":null},{"id":"2311.13541","title":"Linear Log-Normal Attention with Unbiased Concentration","created":"2023-11-22","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":"2408.14811","title":"Brain-inspired Artificial Intelligence: A Comprehensive Review","created":"2024-08-27","cited_by_count":9,"area":null},{"id":"2503.04725","title":"L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling","created":"2025-03-06","cited_by_count":9,"area":null},{"id":"2505.19959","title":"MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language Models","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2204.10670","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","created":"2022-04-22","cited_by_count":6,"area":null},{"id":"2302.08374","title":"Efficiency 360: Efficient Vision Transformers","created":"2023-02-16","cited_by_count":6,"area":null},{"id":"2402.18508","title":"Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling","created":"2024-02-28","cited_by_count":6,"area":null},{"id":"2405.17534","title":"SMR: State Memory Replay for Long Sequence Modeling","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2508.14112","title":"Surya: Foundation Model for Heliophysics","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2110.02442","title":"PoNet: Pooling Network for Efficient Token Mixing in Long Sequences","created":"2021-10-06","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":"2407.16847","title":"SPLAT: A framework for optimised GPU code-generation for SParse reguLar ATtention","created":"2024-07-23","cited_by_count":5,"area":null},{"id":"2203.12644","title":"Linearizing Transformer with Key-Value Memory","created":"2022-03-23","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":"2312.11135","title":"Linear Attention via Orthogonal Memory","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2404.11163","title":"LongVQ: Long Sequence Modeling with Vector Quantization on Structured Memory","created":"2024-04-17","cited_by_count":4,"area":null},{"id":"2406.01559","title":"Prototypical Transformer as Unified Motion Learners","created":"2024-06-03","cited_by_count":4,"area":null},{"id":"2406.13781","title":"A Primal-Dual Framework for Transformers and Neural Networks","created":"2024-06-19","cited_by_count":4,"area":null},{"id":"2503.12355","title":"Atlas: Multi-Scale Attention Improves Long Context Image Modeling","created":"2025-03-16","cited_by_count":4,"area":null},{"id":"2204.11045","title":"Investigating Neural Architectures by Synthetic Dataset Design","created":"2022-04-23","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":"2401.03540","title":"SeTformer is What You Need for Vision and Language","created":"2024-01-07","cited_by_count":3,"area":null},{"id":"2410.23222","title":"Dataset-Driven Channel Masks in Transformers for Multivariate Time Series","created":"2024-10-30","cited_by_count":3,"area":null},{"id":"2109.08184","title":"Sparse Factorization of Large Square Matrices","created":"2021-09-16","cited_by_count":2,"area":null},{"id":"2203.14557","title":"Visual Mechanisms Inspired Efficient Transformers for Image and Video Quality Assessment","created":"2022-03-28","cited_by_count":2,"area":null},{"id":"2301.09416","title":"Towards Robust Video Instance Segmentation with Temporal-Aware Transformer","created":"2023-01-20","cited_by_count":2,"area":null},{"id":"2303.13340","title":"Increasing Textual Context Size Boosts Medical Image-Text Matching","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2312.12742","title":"Cached Transformers: Improving Transformers with Differentiable Memory Cache","created":"2023-12-20","cited_by_count":2,"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":"2505.20048","title":"Synthetic Time Series Forecasting with Transformer Architectures: Extensive Simulation Benchmarks","created":"2025-05-26","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":"2510.05901","title":"Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2309.14174","title":"Only 5\\% Attention Is All You Need: Efficient Long-range Document-level Neural Machine Translation","created":"2023-09-25","cited_by_count":1,"area":null},{"id":"2402.17507","title":"Interactive Multi-Head Self-Attention with Linear Complexity","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2404.05210","title":"Bidirectional Long-Range Parser for Sequential Data Understanding","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2412.06106","title":"Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling","created":"2024-12-08","cited_by_count":1,"area":null},{"id":"2503.23174","title":"TRA: Better Length Generalisation with Threshold Relative Attention","created":"2025-03-29","cited_by_count":1,"area":null},{"id":"2509.15448","title":"Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems","created":"2025-09-18","cited_by_count":1,"area":null},{"id":"2302.00340","title":"Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture","created":"2023-02-01","cited_by_count":0,"area":null},{"id":"2306.01768","title":"A Quantitative Review on Language Model Efficiency Research","created":"2023-05-28","cited_by_count":0,"area":null},{"id":"2306.01929","title":"Recent Advances of Local Mechanisms in Computer Vision: A Survey and Outlook of Recent Work","created":"2023-06-02","cited_by_count":0,"area":null},{"id":"2310.07664","title":"Accelerating Vision Transformers Based on Heterogeneous Attention Patterns","created":"2023-10-11","cited_by_count":0,"area":null},{"id":"2407.09852","title":"Free-form Grid Structure Form Finding based on Machine Learning and Multi-objective Optimisation","created":"2024-07-13","cited_by_count":0,"area":null},{"id":"2408.05391","title":"SAMSA: Efficient Transformer for Many Data Modalities","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2410.00380","title":"GLMHA A Guided Low-rank Multi-Head Self-Attention for Efficient Image Restoration and Spectral Reconstruction","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2503.10655","title":"Language modelling techniques for analysing the impact of human genetic variation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2504.13981","title":"CacheFormer: High Attention-Based Segment Caching","created":"2025-04-18","cited_by_count":0,"area":null},{"id":"2601.17641","title":"RPNT: Robust Pre-trained Neural Transformer -- A Pathway for Generalized Motor Decoding","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2607.03652","title":"ELiTeFormer: An Efficient Transformer for FPGAs","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.11211","title":"FastTPS: An Optimized Method for LLM Token Phase for AI accelerators","created":"2026-07-13","cited_by_count":0,"area":null}],"next_cursor":null}