{"total":98,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718,"area":"ssm"},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336,"area":"ssm"},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"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":"2407.04620","title":"Learning to (Learn at Test Time): RNNs with Expressive Hidden States","created":"2024-07-05","cited_by_count":355,"area":"ssm"},{"id":"2506.13585","title":"MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention","created":"2025-06-16","cited_by_count":263,"area":"lr"},{"id":"2307.02486","title":"LongNet: Scaling Transformers to 1,000,000,000 Tokens","created":"2023-07-05","cited_by_count":204,"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":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2401.12973","title":"In-Context Language Learning: Architectures and Algorithms","created":"2024-01-23","cited_by_count":89,"area":null},{"id":"2409.07146","title":"Gated Slot Attention for Efficient Linear-Time Sequence Modeling","created":"2024-09-11","cited_by_count":76,"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":"2401.04658","title":"Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models","created":"2024-01-09","cited_by_count":57,"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":"2407.09941","title":"Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers","created":"2024-07-13","cited_by_count":44,"area":"ssm"},{"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":"2405.16156","title":"Mixture of In-Context Prompters for Tabular PFNs","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2402.06262","title":"On the Efficacy of Eviction Policy for Key-Value Constrained Generative Language Model Inference","created":"2024-02-09","cited_by_count":32,"area":"inference"},{"id":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31,"area":null},{"id":"2410.10254","title":"LoLCATs: On Low-Rank Linearizing of Large Language Models","created":"2024-10-14","cited_by_count":27,"area":null},{"id":"2304.03589","title":"On Efficient Training of Large-Scale Deep Learning Models: A Literature Review","created":"2023-04-07","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":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","cited_by_count":21,"area":null},{"id":"2505.23947","title":"Position: The Future of Bayesian Prediction Is Prior-Fitted","created":"2025-05-29","cited_by_count":20,"area":null},{"id":"2504.05646","title":"Lattice: Learning to Efficiently Compress the Memory","created":"2025-04-08","cited_by_count":19,"area":null},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","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":"2401.16265","title":"CO2: Efficient Distributed Training with Full Communication-Computation Overlap","created":"2024-01-29","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":"2602.01077","title":"PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers","created":"2026-02-01","cited_by_count":17,"area":"diffusion"},{"id":"2410.02719","title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","created":"2024-10-03","cited_by_count":16,"area":"rag"},{"id":"2507.00698","title":"Rectifying Magnitude Neglect in Linear Attention","created":"2025-07-01","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":"2506.05584","title":"TabFlex: Scaling Tabular Learning to Millions with Linear Attention","created":"2025-06-05","cited_by_count":15,"area":null},{"id":"2505.00315","title":"Mixture of Sparse Attention: Content-Based Learnable Sparse Attention via Expert-Choice Routing","created":"2025-05-01","cited_by_count":14,"area":"moe"},{"id":"2510.04800","title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","created":"2025-10-06","cited_by_count":14,"area":"ssm"},{"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":"2405.18425","title":"ViG: Linear-complexity Visual Sequence Learning with Gated Linear Attention","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2503.14376","title":"Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels","created":"2025-03-18","cited_by_count":13,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"area":null},{"id":"2403.09347","title":"BurstAttention: An Efficient Distributed Attention Framework for Extremely Long Sequences","created":"2024-03-14","cited_by_count":10,"area":null},{"id":"2405.08553","title":"Improving Transformers with Dynamically Composable Multi-Head Attention","created":"2024-05-14","cited_by_count":10,"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":"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":"2501.14577","title":"ZETA: Leveraging Z-order Curves for Efficient Top-k Attention","created":"2025-01-24","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":"2504.12959","title":"Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction","created":"2025-04-17","cited_by_count":9,"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":"2404.02945","title":"Optimizing the Deployment of Tiny Transformers on Low-Power MCUs","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"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":"2503.10252","title":"SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning","created":"2025-03-13","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":"2602.05230","title":"ZeroS: Zero-Sum Linear Attention for Efficient Transformers","created":"2026-02-05","cited_by_count":5,"area":null},{"id":"2409.15104","title":"PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference","created":"2024-09-23","cited_by_count":4,"area":null},{"id":"2502.01578","title":"ReGLA: Refining Gated Linear Attention","created":"2025-02-03","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":"2604.03582","title":"Simple yet Effective: Low-Rank Spatial Attention for Neural Operators","created":"2026-04-04","cited_by_count":4,"area":null},{"id":"2308.04321","title":"All-pairs Consistency Learning for Weakly Supervised Semantic Segmentation","created":"2023-08-08","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":"2407.02423","title":"On the Anatomy of Attention","created":"2024-07-02","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":"2505.01475","title":"CodeSSM: Towards State Space Models for Code Understanding","created":"2025-05-02","cited_by_count":3,"area":null},{"id":"2509.18467","title":"LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modeling","created":"2025-09-22","cited_by_count":3,"area":null},{"id":"2510.12251","title":"DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2511.00907","title":"Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle","created":"2025-11-02","cited_by_count":3,"area":null},{"id":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2405.13046","title":"LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions","created":"2024-05-18","cited_by_count":2,"area":null},{"id":"2502.19823","title":"GraphSparseNet: a Novel Method for Large Scale Traffic Flow Prediction","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2602.07160","title":"Free Energy Mixer","created":"2026-02-06","cited_by_count":2,"area":null},{"id":"2603.20842","title":"A Knowledge-Informed Pretrained Model for Causal Discovery","created":"2026-03-21","cited_by_count":2,"area":null},{"id":"2305.16340","title":"Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model","created":"2023-05-24","cited_by_count":1,"area":null},{"id":"2402.07901","title":"FAST: Factorizable Attention for Speeding up Transformers","created":"2024-02-12","cited_by_count":1,"area":null},{"id":"2407.18601","title":"Reorganizing attention-space geometry with expressive attention","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2504.01257","title":"FLAMES: A Hybrid Spiking-State Space Model for Adaptive Memory Retention in Event-Based Learning","created":"2025-04-02","cited_by_count":1,"area":null},{"id":"2507.07396","title":"IML-Spikeformer: Input-aware Multi-Level Spiking Transformer for Speech Processing","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2509.05282","title":"Elucidating the Design Space of Decay in Linear Attention","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2510.21956","title":"Transformer Based Linear Attention with Optimized GPU Kernel Implementation","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2512.10252","title":"GDKVM: Echocardiography Video Segmentation via Spatiotemporal Key-Value Memory with Gated Delta Rule","created":"2025-12-11","cited_by_count":1,"area":null},{"id":"2602.03922","title":"Online Vector Quantized Attention","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2605.06611","title":"The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2605.29622","title":"M\\=oLe-{\\Lambda}: Learning the Coupled-Cluster Response State for Energies, Gradients, and Properties","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2512.12219","title":"Fine-Grained Zero-Shot Learning with Attribute-Centric Representations","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2602.20232","title":"Coupled Cluster con M\\=oLe: Molecular Orbital Learning for Neural Wavefunctions","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.02727","title":"Gated Differential Linear Attention: A Linear-Time Decoder for High-Fidelity Medical Segmentation","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2603.02886","title":"StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting","created":"2026-03-03","cited_by_count":0,"area":null},{"id":"2604.10064","title":"On The Application of Linear Attention in Multimodal Transformers","created":"2026-04-11","cited_by_count":0,"area":"mllm"},{"id":"2604.18967","title":"CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.18848","title":"Exact Linear Attention","created":"2026-05-13","cited_by_count":0,"area":"moe"},{"id":"2608.11519","title":"FLARE++: Low-rank attention with dynamic attention routing","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.20069","title":"V-REX: Efficient Specialist VLM Training for Veterinary X-Rays","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2609.10810","title":"Larger Context Window, Fewer Overcorrections: Optimizing Prompts and Batching for Minimal-Edit Grammatical Error Correction","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.36259","title":"CyFA: Linear Sequence Modeling with Relative-Time-Partitioned Memory","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}