{"total":107,"rows":[{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471,"area":null},{"id":"2106.04554","title":"A Survey of Transformers","created":"2021-06-08","cited_by_count":401,"area":null},{"id":"2105.03824","title":"FNet: Mixing Tokens with Fourier Transforms","created":"2021-05-09","cited_by_count":347,"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":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163,"area":null},{"id":"2205.12257","title":"OnePose: One-Shot Object Pose Estimation without CAD Models","created":"2022-05-24","cited_by_count":157,"area":null},{"id":"2305.05465","title":"The emergence of clusters in self-attention dynamics","created":"2023-05-09","cited_by_count":140,"area":null},{"id":"2305.01625","title":"Unlimiformer: Long-Range Transformers with Unlimited Length Input","created":"2023-05-02","cited_by_count":128,"area":null},{"id":"2203.10314","title":"Voxel Set Transformer: A Set-to-Set Approach to 3D Object Detection from Point Clouds","created":"2022-03-19","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":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2110.03860","title":"Token Pooling in Vision Transformers","created":"2021-10-08","cited_by_count":69,"area":null},{"id":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65,"area":null},{"id":"2112.01898","title":"Linear algebra with transformers","created":"2021-12-03","cited_by_count":63,"area":null},{"id":"2106.06899","title":"Memory-efficient Transformers via Top-$k$ Attention","created":"2021-06-13","cited_by_count":60,"area":null},{"id":"2406.16747","title":"Sparser is Faster and Less is More: Efficient Sparse Attention for Long-Range Transformers","created":"2024-06-24","cited_by_count":52,"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":"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":"2112.09686","title":"Efficient Visual Tracking with Exemplar Transformers","created":"2021-12-17","cited_by_count":48,"area":null},{"id":"2106.03764","title":"On the Expressive Power of Self-Attention Matrices","created":"2021-06-07","cited_by_count":47,"area":null},{"id":"2106.11958","title":"Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation","created":"2021-06-22","cited_by_count":43,"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":"2403.13347","title":"vid-TLDR: Training Free Token merging for Light-weight Video Transformer","created":"2024-03-20","cited_by_count":41,"area":null},{"id":"2111.12480","title":"Octree Transformer: Autoregressive 3D Shape Generation on Hierarchically Structured Sequences","created":"2021-11-24","cited_by_count":39,"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":"2106.01401","title":"Container: Context Aggregation Network","created":"2021-06-02","cited_by_count":37,"area":null},{"id":"2204.07756","title":"Visual Attention Methods in Deep Learning: An In-Depth Survey","created":"2022-04-16","cited_by_count":37,"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":"2110.02488","title":"ABC: Attention with Bounded-memory Control","created":"2021-10-06","cited_by_count":36,"area":null},{"id":"2410.20399","title":"ThunderKittens: Simple, Fast, and Adorable AI Kernels","created":"2024-10-27","cited_by_count":36,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2210.01035","title":"Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning","created":"2022-10-03","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":"2108.02347","title":"FMMformer: Efficient and Flexible Transformer via Decomposed Near-field and Far-field Attention","created":"2021-08-05","cited_by_count":26,"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":"2302.04542","title":"Efficient Attention via Control Variates","created":"2023-02-09","cited_by_count":23,"area":null},{"id":"2112.13776","title":"Transformer Uncertainty Estimation with Hierarchical Stochastic Attention","created":"2021-12-27","cited_by_count":21,"area":null},{"id":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","cited_by_count":21,"area":null},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20,"area":null},{"id":"2101.09755","title":"RomeBERT: Robust Training of Multi-Exit BERT","created":"2021-01-24","cited_by_count":19,"area":null},{"id":"2110.05722","title":"LightSeq2: Accelerated Training for Transformer-based Models on GPUs","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2308.12383","title":"With a Little Help from your own Past: Prototypical Memory Networks for Image Captioning","created":"2023-08-23","cited_by_count":18,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2303.03565","title":"CLIP-Layout: Style-Consistent Indoor Scene Synthesis with Semantic Furniture Embedding","created":"2023-03-07","cited_by_count":16,"area":null},{"id":"2503.06896","title":"CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution","created":"2025-03-10","cited_by_count":16,"area":null},{"id":"2206.08194","title":"Online Segmentation of LiDAR Sequences: Dataset and Algorithm","created":"2022-06-16","cited_by_count":14,"area":null},{"id":"2109.12188","title":"Predicting Attention Sparsity in Transformers","created":"2021-09-24","cited_by_count":13,"area":null},{"id":"2210.11794","title":"Diffuser: Efficient Transformers with Multi-hop Attention Diffusion for Long Sequences","created":"2022-10-21","cited_by_count":12,"area":null},{"id":"2410.14195","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","created":"2024-10-18","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":"2410.10759","title":"SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization","created":"2024-10-14","cited_by_count":11,"area":null},{"id":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","cited_by_count":10,"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":"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":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"area":null},{"id":"2304.12406","title":"AutoFocusFormer: Image Segmentation off the Grid","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2406.14830","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","created":"2024-06-21","cited_by_count":9,"area":null},{"id":"2504.16795","title":"Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access","created":"2025-04-23","cited_by_count":9,"area":null},{"id":"2511.21317","title":"HTTM: Head-wise Temporal Token Merging for Faster VGGT","created":"2025-11-26","cited_by_count":9,"area":null},{"id":"2109.00301","title":"$\\infty$-former: Infinite Memory Transformer","created":"2021-09-01","cited_by_count":7,"area":null},{"id":"2406.08152","title":"CT3D++: Improving 3D Object Detection with Keypoint-induced Channel-wise Transformer","created":"2024-06-12","cited_by_count":7,"area":null},{"id":"2103.09857","title":"Value-aware Approximate Attention","created":"2021-03-17","cited_by_count":5,"area":null},{"id":"2305.11862","title":"Reducing Sequence Length by Predicting Edit Operations with Large Language Models","created":"2023-05-19","cited_by_count":5,"area":null},{"id":"2310.15494","title":"TRAMS: Training-free Memory Selection for Long-range Language Modeling","created":"2023-10-24","cited_by_count":5,"area":null},{"id":"2411.01431","title":"Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision","created":"2024-11-03","cited_by_count":5,"area":null},{"id":"2207.04293","title":"Attention and Self-Attention in Random Forests","created":"2022-07-09","cited_by_count":4,"area":null},{"id":"2208.00579","title":"Momentum Transformer: Closing the Performance Gap Between Self-attention and Its Linearization","created":"2022-08-01","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":"2410.18926","title":"LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search","created":"2024-10-24","cited_by_count":4,"area":null},{"id":"2112.03588","title":"A deep language model to predict metabolic network equilibria","created":"2021-12-07","cited_by_count":3,"area":null},{"id":"2210.13944","title":"A Survey on Artificial Intelligence for Music Generation: Agents, Domains and Perspectives","created":"2022-10-25","cited_by_count":3,"area":null},{"id":"2301.12444","title":"Exploring Attention Map Reuse for Efficient Transformer Neural Networks","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2310.11960","title":"Fast Multipole Attention: A Scalable Multilevel Attention Mechanism for Text and Images","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2311.12885","title":"Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis","created":"2023-11-21","cited_by_count":3,"area":null},{"id":"2401.17604","title":"Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition","created":"2024-01-31","cited_by_count":3,"area":null},{"id":"2105.02282","title":"Attention for Image Registration (AiR): an unsupervised Transformer approach","created":"2021-05-05","cited_by_count":2,"area":null},{"id":"2108.04962","title":"Adaptive Multi-Resolution Attention with Linear Complexity","created":"2021-08-10","cited_by_count":2,"area":null},{"id":"2206.15312","title":"FL-Tuning: Layer Tuning for Feed-Forward Network in Transformer","created":"2022-06-30","cited_by_count":2,"area":null},{"id":"2209.00281","title":"Large-Scale Auto-Regressive Modeling Of Street Networks","created":"2022-09-01","cited_by_count":2,"area":null},{"id":"2503.10571","title":"Radar: Fast Long-Context Decoding for Any Transformer","created":"2025-03-13","cited_by_count":2,"area":null},{"id":"2509.15958","title":"Localmax dynamics for attention in transformers and its asymptotic behavior","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2201.09145","title":"glassoformer: a query-sparse transformer for post-fault power grid voltage prediction","created":"2022-01-22","cited_by_count":1,"area":null},{"id":"2208.05152","title":"TagRec++: Hierarchical Label Aware Attention Network for Question Categorization","created":"2022-08-10","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":"2409.07541","title":"ENACT: Entropy-based Clustering of Attention Input for Reducing the Computational Needs of Object Detection Transformers","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2502.20393","title":"Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models","created":"2025-02-27","cited_by_count":1,"area":null},{"id":"2511.08260","title":"Data-Driven Discovery of Feature Groups in Clinical Time Series","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2605.13465","title":"Z-Order Transformer for Feed-Forward Gaussian Splatting","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.12789","title":"AVQ-Attention: Adaptive Vector-Quantized Attention","created":"2026-07-14","cited_by_count":1,"area":null},{"id":"2107.03742","title":"Grid Partitioned Attention: Efficient TransformerApproximation with Inductive Bias for High Resolution Detail Generation","created":"2021-07-08","cited_by_count":0,"area":null},{"id":"2311.05089","title":"Legal-HNet: Mixing Legal Long-Context Tokens with Hartley Transform","created":"2023-11-09","cited_by_count":0,"area":null},{"id":"2403.02411","title":"NiNformer: A Network in Network Transformer with Token Mixing Generated Gating Function","created":"2024-03-04","cited_by_count":0,"area":null},{"id":"2405.15953","title":"Activator: GLU Activation Function as the Core Component of a Vision Transformer","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2407.04991","title":"The Solution for the AIGC Inference Performance Optimization Competition","created":"2024-07-06","cited_by_count":0,"area":null}],"next_cursor":"100"}