{"total":128,"rows":[{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329,"area":"diffusion"},{"id":"2308.00442","title":"FLatten Transformer: Vision Transformer using Focused Linear Attention","created":"2023-08-01","cited_by_count":171,"area":null},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139,"area":null},{"id":"2303.03667","title":"Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks","created":"2023-03-07","cited_by_count":130,"area":null},{"id":"2205.03436","title":"EdgeViTs: Competing Light-weight CNNs on Mobile Devices with Vision Transformers","created":"2022-05-06","cited_by_count":116,"area":null},{"id":"2405.16605","title":"Demystify Mamba in Vision: A Linear Attention Perspective","created":"2024-05-26","cited_by_count":102,"area":"ssm"},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2403.01590","title":"The Hidden Attention of Mamba Models","created":"2024-03-03","cited_by_count":91,"area":"ssm"},{"id":"2312.08874","title":"Agent Attention: On the Integration of Softmax and Linear Attention","created":"2023-12-14","cited_by_count":90,"area":null},{"id":"2402.02244","title":"Beyond the Limits: A Survey of Techniques to Extend the Context Length in Large Language Models","created":"2024-02-03","cited_by_count":76,"area":"lr"},{"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":"2202.06258","title":"Flowformer: Linearizing Transformers with Conservation Flows","created":"2022-02-13","cited_by_count":69,"area":null},{"id":"2306.06189","title":"FasterViT: Fast Vision Transformers with Hierarchical Attention","created":"2023-06-09","cited_by_count":65,"area":null},{"id":"2206.00216","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","created":"2022-06-01","cited_by_count":57,"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":"2309.08586","title":"Replacing softmax with ReLU in Vision Transformers","created":"2023-09-15","cited_by_count":44,"area":null},{"id":"2309.02031","title":"A survey on efficient vision transformers: algorithms, techniques, and performance benchmarking","created":"2023-09-05","cited_by_count":41,"area":null},{"id":"2302.04931","title":"In-Context Learning with Many Demonstration Examples","created":"2023-02-09","cited_by_count":39,"area":null},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39,"area":"ssm"},{"id":"2210.06462","title":"Self-Guided Diffusion Models","created":"2022-10-12","cited_by_count":37,"area":"diffusion"},{"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":"2303.11316","title":"Generative Semantic Segmentation","created":"2023-03-20","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":"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":"2308.04549","title":"Prune Spatio-temporal Tokens by Semantic-aware Temporal Accumulation","created":"2023-08-08","cited_by_count":24,"area":null},{"id":"2408.05710","title":"Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators","created":"2024-08-11","cited_by_count":24,"area":"diffusion"},{"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":"2209.09004","title":"EcoFormer: Energy-Saving Attention with Linear Complexity","created":"2022-09-19","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":"2311.03035","title":"GTP-ViT: Efficient Vision Transformers via Graph-based Token Propagation","created":"2023-11-06","cited_by_count":19,"area":"inference"},{"id":"2112.12786","title":"ELSA: Enhanced Local Self-Attention for Vision Transformer","created":"2021-12-23","cited_by_count":18,"area":null},{"id":"2310.13807","title":"Learning to (Learn at Test Time)","created":"2023-10-20","cited_by_count":17,"area":null},{"id":"2405.09285","title":"Positional Knowledge is All You Need: Position-induced Transformer (PiT) for Operator Learning","created":"2024-05-15","cited_by_count":17,"area":null},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17,"area":null},{"id":"2112.11685","title":"Cost Aggregation Is All You Need for Few-Shot Segmentation","created":"2021-12-22","cited_by_count":16,"area":null},{"id":"2304.03369","title":"EGA-Depth: Efficient Guided Attention for Self-Supervised Multi-Camera Depth Estimation","created":"2023-04-06","cited_by_count":16,"area":null},{"id":"2401.15235","title":"CascadedGaze: Efficiency in Global Context Extraction for Image Restoration","created":"2024-01-26","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":"2210.12333","title":"Accumulated Trivial Attention Matters in Vision Transformers on Small Datasets","created":"2022-10-22","cited_by_count":15,"area":null},{"id":"2306.06446","title":"ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer","created":"2023-06-10","cited_by_count":15,"area":"moe"},{"id":"2310.13220","title":"Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens","created":"2023-10-20","cited_by_count":15,"area":null},{"id":"2203.00091","title":"Dynamic N:M Fine-grained Structured Sparse Attention Mechanism","created":"2022-02-28","cited_by_count":14,"area":null},{"id":"2308.13998","title":"Computation-efficient Deep Learning for Computer Vision: A Survey","created":"2023-08-27","cited_by_count":14,"area":null},{"id":"2403.11120","title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","created":"2024-03-17","cited_by_count":14,"area":null},{"id":"2404.10407","title":"Comprehensive Survey of Model Compression and Speed up for Vision Transformers","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2308.13494","title":"Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","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":"2307.05979","title":"Transformers in Reinforcement Learning: A Survey","created":"2023-07-12","cited_by_count":12,"area":null},{"id":"2207.10284","title":"Multi Resolution Analysis (MRA) for Approximate Self-Attention","created":"2022-07-21","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":"2210.16897","title":"Time-rEversed diffusioN tEnsor Transformer: A new TENET of Few-Shot Object Detection","created":"2022-10-30","cited_by_count":10,"area":null},{"id":"2211.15595","title":"FsaNet: Frequency Self-attention for Semantic Segmentation","created":"2022-11-28","cited_by_count":10,"area":null},{"id":"2312.16045","title":"Algebraic Positional Encodings","created":"2023-12-26","cited_by_count":10,"area":null},{"id":"2406.19006","title":"Snakes and Ladders: Two Steps Up for VideoMamba","created":"2024-06-27","cited_by_count":10,"area":"ssm"},{"id":"2207.03341","title":"Softmax-free Linear Transformers","created":"2022-07-05","cited_by_count":9,"area":null},{"id":"2209.09545","title":"Graph Reasoning Transformer for Image Parsing","created":"2022-09-20","cited_by_count":9,"area":null},{"id":"2212.11115","title":"What Makes for Good Tokenizers in Vision Transformer?","created":"2022-12-21","cited_by_count":9,"area":null},{"id":"2406.07368","title":"When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models","created":"2024-06-11","cited_by_count":9,"area":"inference"},{"id":"2302.02744","title":"AMD-HookNet for Glacier Front Segmentation","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2209.08742","title":"Integrative Feature and Cost Aggregation with Transformers for Dense Correspondence","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2408.16978","title":"Training Ultra Long Context Language Model with Fully Pipelined Distributed Transformer","created":"2024-08-30","cited_by_count":6,"area":null},{"id":"2409.15298","title":"Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model","created":"2024-09-04","cited_by_count":6,"area":null},{"id":"2511.05924","title":"DiScoFormer: Plug-In Density and Score Estimation with Transformers","created":"2025-11-08","cited_by_count":6,"area":null},{"id":"2207.07564","title":"Rethinking Attention Mechanism in Time Series Classification","created":"2022-07-14","cited_by_count":5,"area":null},{"id":"2212.05599","title":"Orthogonal SVD Covariance Conditioning and Latent Disentanglement","created":"2022-12-11","cited_by_count":5,"area":null},{"id":"2403.05794","title":"Privacy-Preserving Diffusion Model Using Homomorphic Encryption","created":"2024-03-09","cited_by_count":5,"area":"diffusion"},{"id":"2404.12804","title":"Linearly-evolved Transformer for Pan-sharpening","created":"2024-04-19","cited_by_count":5,"area":null},{"id":"2411.16170","title":"CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction","created":"2024-11-25","cited_by_count":5,"area":null},{"id":"2411.18425","title":"Streamlining Prediction in Bayesian Deep Learning","created":"2024-11-27","cited_by_count":5,"area":null},{"id":"2501.14970","title":"AI-driven Wireless Positioning: Fundamentals, Standards, State-of-the-art, and Challenges","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2506.22762","title":"VSRM: A Robust Mamba-Based Framework for Video Super-Resolution","created":"2025-06-28","cited_by_count":5,"area":"ssm"},{"id":"2207.02119","title":"Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2305.07931","title":"GSB: Group Superposition Binarization for Vision Transformer with Limited Training Samples","created":"2023-05-13","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":"2407.11946","title":"Hierarchical Separable Video Transformer for Snapshot Compressive Imaging","created":"2024-07-16","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":"2501.12381","title":"Parallel Sequence Modeling via Generalized Spatial Propagation Network","created":"2025-01-21","cited_by_count":4,"area":null},{"id":"2502.02209","title":"On the Expressivity of Selective State-Space Layers: A Multivariate Polynomial Approach","created":"2025-02-04","cited_by_count":4,"area":"ssm"},{"id":"2504.03738","title":"Attention in Diffusion Model: A Survey","created":"2025-04-01","cited_by_count":4,"area":"diffusion"},{"id":"2505.08516","title":"Learning Advanced Self-Attention for Linear Transformers in the Singular Value Domain","created":"2025-05-13","cited_by_count":4,"area":null},{"id":"2511.00833","title":"Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials","created":"2025-11-02","cited_by_count":4,"area":null},{"id":"2212.12552","title":"A Close Look at Spatial Modeling: From Attention to Convolution","created":"2022-12-23","cited_by_count":3,"area":null},{"id":"2310.02544","title":"SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers","created":"2023-10-04","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":"2405.20867","title":"Automatic Channel Pruning for Multi-Head Attention","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2604.20368","title":"LaplacianFormer:Rethinking Linear Attention with Laplacian Kernel","created":"2026-04-22","cited_by_count":3,"area":null},{"id":"2606.04032","title":"Do Transformers Need Three Projections? Systematic Study of QKV Variants","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2207.13423","title":"Rethinking Efficacy of Softmax for Lightweight Non-Local Neural Networks","created":"2022-07-27","cited_by_count":2,"area":null},{"id":"2310.04466","title":"HartleyMHA: Self-Attention in Frequency Domain for Resolution-Robust and Parameter-Efficient 3D Image Segmentation","created":"2023-10-05","cited_by_count":2,"area":null},{"id":"2401.01470","title":"TPC-ViT: Token Propagation Controller for Efficient Vision Transformer","created":"2024-01-03","cited_by_count":2,"area":null},{"id":"2403.02360","title":"Towards Optimal Customized Architecture for Heterogeneous Federated Learning with Contrastive Cloud-Edge Model Decoupling","created":"2024-03-04","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"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}],"next_cursor":"100"}