{"total":92,"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":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393,"area":null},{"id":"2402.19427","title":"Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models","created":"2024-02-29","cited_by_count":242,"area":null},{"id":"2106.16031","title":"ResViT: Residual vision transformers for multi-modal medical image synthesis","created":"2021-06-30","cited_by_count":177,"area":null},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162,"area":null},{"id":"2404.05892","title":"Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence","created":"2024-04-08","cited_by_count":159,"area":null},{"id":"2202.13556","title":"Filter-enhanced MLP is All You Need for Sequential Recommendation","created":"2022-02-28","cited_by_count":96,"area":null},{"id":"2210.00077","title":"E-Branchformer: Branchformer with Enhanced merging for speech recognition","created":"2022-09-30","cited_by_count":92,"area":null},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"id":"2302.13939","title":"SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks","created":"2023-02-27","cited_by_count":88,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2512.23675","title":"End-to-End Test-Time Training for Long Context","created":"2025-12-29","cited_by_count":62,"area":null},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59,"area":null},{"id":"2209.07484","title":"Hydra Attention: Efficient Attention with Many Heads","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2405.06640","title":"Linearizing Large Language Models","created":"2024-05-10","cited_by_count":51,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2210.02396","title":"Temporally Consistent Transformers for Video Generation","created":"2022-10-05","cited_by_count":44,"area":null},{"id":"2210.04243","title":"Fine-Tuning Pre-trained Transformers into Decaying Fast Weights","created":"2022-10-09","cited_by_count":26,"area":null},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26,"area":null},{"id":"2405.20131","title":"Language Models Need Inductive Biases to Count Inductively","created":"2024-05-30","cited_by_count":25,"area":null},{"id":"2406.02528","title":"Scalable MatMul-free Language Modeling","created":"2024-06-04","cited_by_count":25,"area":null},{"id":"2403.00818","title":"DenseMamba: State Space Models with Dense Hidden Connection for Efficient Large Language Models","created":"2024-02-26","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":"2405.06067","title":"HMT: Hierarchical Memory Transformer for Efficient Long Context Language Processing","created":"2024-05-09","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":"2310.08049","title":"Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability","created":"2023-10-12","cited_by_count":17,"area":null},{"id":"2402.08132","title":"On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era","created":"2024-02-12","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":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","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":"2211.15069","title":"FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network","created":"2022-11-28","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":"2304.12406","title":"AutoFocusFormer: Image Segmentation off the Grid","created":"2023-04-24","cited_by_count":9,"area":null},{"id":"2405.01906","title":"Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver","created":"2024-05-03","cited_by_count":9,"area":null},{"id":"2502.07244","title":"Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting","created":"2025-02-11","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2206.10075","title":"Counting Varying Density Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2408.16717","title":"GREAT: A Graph Edge Attention Network for the Electric Vehicle Routing Problem with Asymmetric Costs","created":"2024-08-29","cited_by_count":8,"area":null},{"id":"2504.10018","title":"RGB-Event based Pedestrian Attribute Recognition: A Benchmark Dataset and An Asymmetric RWKV Fusion Framework","created":"2025-04-14","cited_by_count":7,"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":"2406.04467","title":"Small-E: Small Language Model with Linear Attention for Efficient Speech Synthesis","created":"2024-06-06","cited_by_count":6,"area":null},{"id":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","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":"2201.03217","title":"Local Information Assisted Attention-free Decoder for Audio Captioning","created":"2022-01-10","cited_by_count":5,"area":null},{"id":"2404.12804","title":"Linearly-evolved Transformer for Pan-sharpening","created":"2024-04-19","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":"2111.13677","title":"SWAT: Spatial Structure Within and Among Tokens","created":"2021-11-26","cited_by_count":4,"area":null},{"id":"2310.20633","title":"Defining a New NLP Playground","created":"2023-10-31","cited_by_count":4,"area":null},{"id":"2510.05364","title":"The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures","created":"2025-10-06","cited_by_count":4,"area":null},{"id":"2510.18870","title":"Triangle Multiplication Is All You Need For Biomolecular Structure Representations","created":"2025-10-21","cited_by_count":4,"area":null},{"id":"2209.09548","title":"An Attention Free Long Short-Term Memory for Time Series Forecasting","created":"2022-09-20","cited_by_count":3,"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":"2404.02684","title":"Cross-Architecture Transfer Learning for Linear-Cost Inference Transformers","created":"2024-04-03","cited_by_count":3,"area":null},{"id":"2410.03159","title":"WAVE: Weighted Autoregressive Varying Gate for Time Series Forecasting","created":"2024-10-04","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":"2306.05176","title":"RRWKV: Capturing Long-range Dependencies in RWKV","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2310.19731","title":"ViR: Towards Efficient Vision Retention Backbones","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2402.02625","title":"Enhancing Transformer RNNs with Multiple Temporal Perspectives","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2406.12230","title":"MCSD: An Efficient Language Model with Diverse Fusion","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2505.02705","title":"Multi-View Learning with Context-Guided Receptance for Image Denoising","created":"2025-05-05","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":"2602.07160","title":"Free Energy Mixer","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2207.10237","title":"SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks","created":"2022-07-21","cited_by_count":1,"area":null},{"id":"2303.13504","title":"ReBotNet: Fast Real-time Video Enhancement","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2304.13119","title":"Application of Transformers for Nonlinear Channel Compensation in Optical Systems","created":"2023-04-25","cited_by_count":1,"area":null},{"id":"2312.11142","title":"Efficiency-oriented approaches for self-supervised speech representation learning","created":"2023-12-18","cited_by_count":1,"area":null},{"id":"2404.05843","title":"Softmax Attention with Constant Cost per Token","created":"2024-04-08","cited_by_count":1,"area":null},{"id":"2406.10906","title":"Breaking the Attention Bottleneck","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2506.11305","title":"Don't Pay Attention","created":"2025-06-12","cited_by_count":1,"area":null},{"id":"2601.11164","title":"SoLA-Vision: Fine-grained Layer-wise Linear Softmax Hybrid Attention","created":"2026-01-16","cited_by_count":1,"area":null},{"id":"2605.08587","title":"Kaczmarz Linear Attention","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.29453","title":"Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2211.02292","title":"Boosting Binary Neural Networks via Dynamic Thresholds Learning","created":"2022-11-04","cited_by_count":0,"area":null},{"id":"2304.10614","title":"An Attention Free Conditional Autoencoder For Anomaly Detection in Cryptocurrencies","created":"2023-04-20","cited_by_count":0,"area":null},{"id":"2305.19365","title":"Vision Transformers for Mobile Applications: A Short Survey","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2308.03429","title":"RCMHA: Relative Convolutional Multi-Head Attention for Natural Language Modelling","created":"2023-08-07","cited_by_count":0,"area":null},{"id":"2401.17948","title":"HyperZ$\\cdot$Z$\\cdot$W Operator Connects Slow-Fast Networks for Full Context Interaction","created":"2024-01-31","cited_by_count":0,"area":null},{"id":"2406.06571","title":"SUBLLM: A Novel Efficient Architecture with Token Sequence Subsampling for LLM","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2409.12719","title":"Multi-Scale Feature Prediction with Auxiliary-Info for Neural Image Compression","created":"2024-09-19","cited_by_count":0,"area":null},{"id":"2410.08681","title":"Efficiently Scanning and Resampling Spatio-Temporal Tasks with Irregular Observations","created":"2024-10-11","cited_by_count":0,"area":null},{"id":"2501.00397","title":"Efficient Relational Context Perception for Knowledge Graph Completion","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2501.15262","title":"TflosYOLO+TFSC: An Accurate and Robust Model for Estimating Flower Count and Flowering Period","created":"2025-01-25","cited_by_count":0,"area":null},{"id":"2507.02917","title":"Echo State Transformer: Attention Over Finite Memories","created":"2025-06-25","cited_by_count":0,"area":null},{"id":"2511.03270","title":"SCALE: Upscaled Continual Learning of Large Language Models","created":"2025-11-05","cited_by_count":0,"area":null},{"id":"2604.19147","title":"Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2604.26422","title":"STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2606.23957","title":"Learning the Koopman Operator using Attention Free Transformers","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.11099","title":"Desc++: Efficient Descriptor Enhancement for Data Association in Existing Visual SLAM Systems","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2608.09468","title":"MixFormer: Linear Transformer with Mixture of Memory Experts","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.34034","title":"ADPTNet: Adaptive with Prescriptive Timescales Non-Linear SSM for Sequence Modelling","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}