{"total":193,"rows":[{"id":"2209.15425","title":"Spikformer: When Spiking Neural Network Meets Transformer","created":"2022-09-29","cited_by_count":271,"area":null},{"id":"2206.13947","title":"Long Range Language Modeling via Gated State Spaces","created":"2022-06-27","cited_by_count":265,"area":null},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171,"area":null},{"id":"2307.01694","title":"Spike-driven Transformer","created":"2023-07-04","cited_by_count":146,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"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":"2306.14893","title":"LongCoder: A Long-Range Pre-trained Language Model for Code Completion","created":"2023-06-26","cited_by_count":112,"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":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"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":"2308.14036","title":"MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing","created":"2023-08-27","cited_by_count":81,"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":"2403.01232","title":"Polynormer: Polynomial-Expressive Graph Transformer in Linear Time","created":"2024-03-02","cited_by_count":65,"area":null},{"id":"2203.07363","title":"Implicit Motion Handling for Video Camouflaged Object Detection","created":"2022-03-14","cited_by_count":60,"area":null},{"id":"2405.06640","title":"Linearizing Large Language Models","created":"2024-05-10","cited_by_count":51,"area":null},{"id":"2412.06590","title":"Bridging the Divide: Reconsidering Softmax and Linear Attention","created":"2024-12-09","cited_by_count":48,"area":null},{"id":"2310.04064","title":"How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation","created":"2023-10-06","cited_by_count":44,"area":null},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43,"area":null},{"id":"2305.04749","title":"Toeplitz Neural Network for Sequence Modeling","created":"2023-05-08","cited_by_count":43,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2404.01882","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","created":"2024-04-02","cited_by_count":39,"area":null},{"id":"2501.04486","title":"MB-TaylorFormer V2: Improved Multi-branch Linear Transformer Expanded by Taylor Formula for Image Restoration","created":"2025-01-08","cited_by_count":36,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2307.14995","title":"TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer","created":"2023-07-27","cited_by_count":34,"area":null},{"id":"2206.01136","title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","created":"2022-06-02","cited_by_count":33,"area":null},{"id":"2206.08898","title":"SimA: Simple Softmax-free Attention for Vision Transformers","created":"2022-06-17","cited_by_count":32,"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":"2401.02020","title":"Spikformer V2: Join the High Accuracy Club on ImageNet with an SNN Ticket","created":"2024-01-04","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":"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":"2205.13891","title":"Transformers from an Optimization Perspective","created":"2022-05-27","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":"2306.01160","title":"Faster Causal Attention Over Large Sequences Through Sparse Flash Attention","created":"2023-06-01","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":"2206.10552","title":"Vicinity Vision Transformer","created":"2022-06-21","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":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2211.03495","title":"How Much Does Attention Actually Attend? Questioning the Importance of Attention in Pretrained Transformers","created":"2022-11-07","cited_by_count":21,"area":null},{"id":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2312.01990","title":"SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2309.16217","title":"GAFlow: Incorporating Gaussian Attention into Optical Flow","created":"2023-09-28","cited_by_count":18,"area":null},{"id":"2512.01643","title":"ViT$^3$: Unlocking Test-Time Training in Vision","created":"2025-12-01","cited_by_count":18,"area":null},{"id":"2207.13955","title":"Neural Architecture Search on Efficient Transformers and Beyond","created":"2022-07-28","cited_by_count":17,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","cited_by_count":17,"area":null},{"id":"2410.01537","title":"Attention layers provably solve single-location regression","created":"2024-10-02","cited_by_count":17,"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":"2507.18074","title":"Neural Architecture Discovery via Autonomous Evolution","created":"2025-07-24","cited_by_count":16,"area":null},{"id":"2310.11685","title":"Why Softmax Attention Outperforms Linear Attention","created":"2023-10-18","cited_by_count":15,"area":null},{"id":"2403.18241","title":"NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation","created":"2024-03-27","cited_by_count":13,"area":null},{"id":"2503.16653","title":"iFlame: Interleaving Full and Linear Attention for Efficient Mesh Generation","created":"2025-03-20","cited_by_count":13,"area":null},{"id":"2505.01996","title":"Always Skip Attention","created":"2025-05-04","cited_by_count":13,"area":null},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"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":"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":"2310.01777","title":"SEA: Sparse Linear Attention with Estimated Attention Mask","created":"2023-10-03","cited_by_count":10,"area":null},{"id":"2509.10534","title":"Decoupling the \"What\" and \"Where\" With Polar Coordinate Positional Embeddings","created":"2025-09-05","cited_by_count":10,"area":null},{"id":"2206.05852","title":"ChordMixer: A Scalable Neural Attention Model for Sequences with Different Lengths","created":"2022-06-12","cited_by_count":9,"area":null},{"id":"2207.12152","title":"Deep Laparoscopic Stereo Matching with Transformers","created":"2022-07-25","cited_by_count":9,"area":null},{"id":"2405.21022","title":"You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet","created":"2024-05-31","cited_by_count":9,"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":"2204.04730","title":"Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective","created":"2022-04-10","cited_by_count":8,"area":null},{"id":"2207.01869","title":"Distance Matters in Human-Object Interaction Detection","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2210.00640","title":"Wide Attention Is The Way Forward For Transformers?","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2307.02690","title":"Scaling In-Context Demonstrations with Structured Attention","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2404.02882","title":"Linear Attention Sequence Parallelism","created":"2024-04-03","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":"2410.18613","title":"Rethinking Attention: Polynomial Alternatives to Softmax in Transformers","created":"2024-10-24","cited_by_count":8,"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":"2305.07239","title":"T-former: An Efficient Transformer for Image Inpainting","created":"2023-05-12","cited_by_count":7,"area":null},{"id":"2402.02362","title":"Unification of Symmetries Inside Neural Networks: Transformer, Feedforward and Neural ODE","created":"2024-02-04","cited_by_count":7,"area":null},{"id":"2405.15622","title":"LAM3D: Large Image-Point-Cloud Alignment Model for 3D Reconstruction from Single Image","created":"2024-05-24","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":"2209.13824","title":"Label Distribution Learning via Implicit Distribution Representation","created":"2022-09-28","cited_by_count":6,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2405.17383","title":"Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2410.06577","title":"Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2507.23632","title":"On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective","created":"2025-07-31","cited_by_count":6,"area":null},{"id":"2209.07634","title":"Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2402.00743","title":"Theoretical Understanding of In-Context Learning in Shallow Transformers with Unstructured Data","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2409.18747","title":"Cottention: Linear Transformers With Cosine Attention","created":"2024-09-27","cited_by_count":5,"area":null},{"id":"2411.12992","title":"MemoryFormer: Minimize Transformer Computation by Removing Fully-Connected Layers","created":"2024-11-20","cited_by_count":5,"area":null},{"id":"2505.18698","title":"MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2505.20802","title":"Leaner Transformers: More Heads, Less Depth","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2510.04008","title":"RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts","created":"2025-10-05","cited_by_count":5,"area":null},{"id":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","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":"2310.04604","title":"PriViT: Vision Transformers for Fast Private Inference","created":"2023-10-06","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":"2403.09377","title":"Introducing Routing Functions to Vision-Language Parameter-Efficient Fine-Tuning with Low-Rank Bottlenecks","created":"2024-03-14","cited_by_count":4,"area":null},{"id":"2408.09624","title":"Attention is a smoothed cubic spline","created":"2024-08-19","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":"2507.01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","created":"2025-07-02","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":"2602.02180","title":"STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs","created":"2026-02-02","cited_by_count":4,"area":null}],"next_cursor":"100"}