{"total":138,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827,"area":null},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519,"area":null},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2305.14788","title":"Adapting Language Models to Compress Contexts","created":"2023-05-24","cited_by_count":356,"area":null},{"id":"2305.07185","title":"MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers","created":"2023-05-12","cited_by_count":170,"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":"2410.02660","title":"How to Train Long-Context Language Models (Effectively)","created":"2024-10-03","cited_by_count":146,"area":null},{"id":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"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":"2210.09298","title":"What Makes Convolutional Models Great on Long Sequence Modeling?","created":"2022-10-17","cited_by_count":87,"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":"2405.17399","title":"Transformers Can Do Arithmetic with the Right Embeddings","created":"2024-05-27","cited_by_count":78,"area":null},{"id":"2302.06646","title":"Simple Hardware-Efficient Long Convolutions for Sequence Modeling","created":"2023-02-13","cited_by_count":62,"area":null},{"id":"2403.17844","title":"Mechanistic Design and Scaling of Hybrid Architectures","created":"2024-03-26","cited_by_count":59,"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":"2305.12095","title":"CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting","created":"2023-05-20","cited_by_count":55,"area":null},{"id":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2212.10544","title":"Pretraining Without Attention","created":"2022-12-20","cited_by_count":51,"area":null},{"id":"2501.18795","title":"Rope to Nope and Back Again: A New Hybrid Attention Strategy","created":"2025-01-30","cited_by_count":47,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"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":"2310.02980","title":"Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors","created":"2023-10-04","cited_by_count":34,"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":"2401.07872","title":"The What, Why, and How of Context Length Extension Techniques in Large Language Models -- A Detailed Survey","created":"2024-01-15","cited_by_count":33,"area":null},{"id":"2603.12513","title":"MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens","created":"2026-03-12","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":"2311.03127","title":"Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs","created":"2023-11-06","cited_by_count":25,"area":null},{"id":"2306.09539","title":"Block-State Transformers","created":"2023-06-15","cited_by_count":24,"area":null},{"id":"2212.00768","title":"Simplifying and Understanding State Space Models with Diagonal Linear RNNs","created":"2022-12-01","cited_by_count":23,"area":null},{"id":"2310.05317","title":"Task-Adaptive Tokenization: Enhancing Long-Form Text Generation Efficacy in Mental Health and Beyond","created":"2023-10-09","cited_by_count":23,"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":"2306.11197","title":"Sparse Modular Activation for Efficient Sequence Modeling","created":"2023-06-19","cited_by_count":20,"area":null},{"id":"2311.08610","title":"Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption","created":"2023-11-15","cited_by_count":19,"area":null},{"id":"2401.00955","title":"Learning Long Sequences in Spiking Neural Networks","created":"2023-12-14","cited_by_count":19,"area":null},{"id":"2306.06635","title":"2-D SSM: A General Spatial Layer for Visual Transformers","created":"2023-06-11","cited_by_count":18,"area":null},{"id":"2410.03464","title":"S7: Selective and Simplified State Space Layers for Sequence Modeling","created":"2024-10-04","cited_by_count":17,"area":null},{"id":"2509.22284","title":"Structured Sparse Transition Matrices to Enable State Tracking in State-Space Models","created":"2025-09-26","cited_by_count":16,"area":null},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15,"area":null},{"id":"2408.04713","title":"DyGMamba: Efficiently Modeling Long-Term Temporal Dependency on Continuous-Time Dynamic Graphs with State Space Models","created":"2024-08-08","cited_by_count":14,"area":null},{"id":"2310.12442","title":"Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer","created":"2023-10-19","cited_by_count":13,"area":null},{"id":"2406.05815","title":"What Can We Learn from State Space Models for Machine Learning on Graphs?","created":"2024-06-09","cited_by_count":13,"area":null},{"id":"2305.14952","title":"Focus Your Attention (with Adaptive IIR Filters)","created":"2023-05-24","cited_by_count":12,"area":null},{"id":"2305.19370","title":"Blockwise Parallel Transformer for Large Context Models","created":"2023-05-30","cited_by_count":12,"area":null},{"id":"2310.20204","title":"General-Purpose Retrieval-Enhanced Medical Prediction Model Using Near-Infinite History","created":"2023-10-31","cited_by_count":12,"area":null},{"id":"2312.02549","title":"DemaFormer: Damped Exponential Moving Average Transformer with Energy-Based Modeling for Temporal Language Grounding","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2409.19315","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2305.17627","title":"Robust Natural Language Understanding with Residual Attention Debiasing","created":"2023-05-28","cited_by_count":10,"area":null},{"id":"2311.16620","title":"On the Long Range Abilities of Transformers","created":"2023-11-28","cited_by_count":10,"area":null},{"id":"2311.15786","title":"YUAN 2.0: A Large Language Model with Localized Filtering-based Attention","created":"2023-11-27","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":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"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":"2407.05591","title":"On the Power of Convolution Augmented Transformer","created":"2024-07-08","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":"2508.12594","title":"FLARE: Fast Low-rank Attention Routing Engine","created":"2025-08-18","cited_by_count":6,"area":null},{"id":"2305.13751","title":"Challenges in Context-Aware Neural Machine Translation","created":"2023-05-23","cited_by_count":5,"area":null},{"id":"2306.16922","title":"The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks","created":"2023-06-14","cited_by_count":5,"area":null},{"id":"2309.13600","title":"Multi-Dimensional Hyena for Spatial Inductive Bias","created":"2023-09-24","cited_by_count":5,"area":null},{"id":"2311.04449","title":"Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2402.00976","title":"Investigating Recurrent Transformers with Dynamic Halt","created":"2024-02-01","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":"2408.10483","title":"PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2302.05400","title":"DNArch: Learning Convolutional Neural Architectures by Backpropagation","created":"2023-02-10","cited_by_count":4,"area":null},{"id":"2402.05370","title":"Attention as Robust Representation for Time Series Forecasting","created":"2024-02-08","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":"2406.05532","title":"Exploring Adversarial Robustness of Deep State Space Models","created":"2024-06-08","cited_by_count":4,"area":null},{"id":"2406.15752","title":"TacoLM: GaTed Attention Equipped Codec Language Model are Efficient Zero-Shot Text to Speech Synthesizers","created":"2024-06-22","cited_by_count":4,"area":null},{"id":"2408.12232","title":"BihoT: A Large-Scale Dataset and Benchmark for Hyperspectral Camouflaged Object Tracking","created":"2024-08-22","cited_by_count":4,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"area":null},{"id":"2502.18394","title":"SPECTRE: An FFT-Based Efficient Drop-In Replacement to Self-Attention for Long Contexts","created":"2025-02-25","cited_by_count":4,"area":null},{"id":"2512.12602","title":"Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics","created":"2025-12-14","cited_by_count":4,"area":null},{"id":"2210.01989","title":"WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability","created":"2022-10-05","cited_by_count":3,"area":null},{"id":"2401.04881","title":"Attendre: Wait To Attend By Retrieval With Evicted Queries in Memory-Based Transformers for Long Context Processing","created":"2024-01-10","cited_by_count":3,"area":null},{"id":"2406.04342","title":"Learning 1D Causal Visual Representation with De-focus Attention Networks","created":"2024-06-06","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":"2410.12982","title":"Flash Inference: Near Linear Time Inference for Long Convolution Sequence Models and Beyond","created":"2024-10-16","cited_by_count":3,"area":null},{"id":"2507.04416","title":"RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling","created":"2025-07-06","cited_by_count":3,"area":null},{"id":"2508.20441","title":"Uncovering the Spectral Bias in Diagonal State Space Models","created":"2025-08-28","cited_by_count":3,"area":null},{"id":"2511.08877","title":"Hierarchical Memorization in Large Language Models: Evidence from Citation Generation","created":"2025-11-12","cited_by_count":3,"area":null},{"id":"2402.02625","title":"Enhancing Transformer RNNs with Multiple Temporal Perspectives","created":"2024-02-04","cited_by_count":2,"area":null},{"id":"2403.17445","title":"Incorporating Exponential Smoothing into MLP: A Simple but Effective Sequence Model","created":"2024-03-26","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":"2408.09453","title":"Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling","created":"2024-08-18","cited_by_count":2,"area":null},{"id":"2410.10914","title":"Towards Better Multi-head Attention via Channel-wise Sample Permutation","created":"2024-10-14","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":"2510.25378","title":"Hallucinations in Bibliographic Recommendation: Citation Frequency as a Proxy for Training Data Redundancy","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2512.23824","title":"MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2301.03127","title":"Logically at Factify 2: A Multi-Modal Fact Checking System Based on Evidence Retrieval techniques and Transformer Encoder Architecture","created":"2023-01-09","cited_by_count":1,"area":null},{"id":"2306.00392","title":"Coneheads: Hierarchy Aware Attention","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2310.05829","title":"USTEP: Spatio-Temporal Predictive Learning under A Unified View","created":"2023-10-09","cited_by_count":1,"area":null},{"id":"2310.14921","title":"PartialFormer: Modeling Part Instead of Whole for Machine Translation","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2310.17683","title":"Sliceformer: Make Multi-head Attention as Simple as Sorting in Discriminative Tasks","created":"2023-10-26","cited_by_count":1,"area":null},{"id":"2401.06762","title":"Seeing the roads through the trees: A benchmark for modeling spatial dependencies with aerial imagery","created":"2024-01-12","cited_by_count":1,"area":null},{"id":"2402.17512","title":"Unifying Linear-Time Attention via Latent Probabilistic Modelling","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2406.07084","title":"Leveraging Large Language Models for Efficient Failure Analysis in Game Development","created":"2024-06-11","cited_by_count":1,"area":null}],"next_cursor":"100"}