{"total":110,"rows":[{"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":"2405.14782","title":"Lessons from the Trenches on Reproducible Evaluation of Language Models","created":"2024-05-23","cited_by_count":179,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"area":null},{"id":"2407.13623","title":"Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies","created":"2024-07-18","cited_by_count":118,"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":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2505.23735","title":"ATLAS: Learning to Optimally Memorize the Context at Test Time","created":"2025-05-29","cited_by_count":66,"area":null},{"id":"2504.13173","title":"It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization","created":"2025-04-17","cited_by_count":64,"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":"2502.13685","title":"MoM: Linear Sequence Modeling with Mixture-of-Memories","created":"2025-02-19","cited_by_count":47,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2407.11087","title":"Restore-RWKV: Efficient and Effective Medical Image Restoration with RWKV","created":"2024-07-14","cited_by_count":36,"area":null},{"id":"2409.15277","title":"A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?","created":"2024-09-23","cited_by_count":33,"area":null},{"id":"2503.01496","title":"Liger: Linearizing Large Language Models to Gated Recurrent Structures","created":"2025-03-03","cited_by_count":33,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2502.12170","title":"MUDDFormer: Breaking Residual Bottlenecks in Transformers via Multiway Dynamic Dense Connections","created":"2025-02-13","cited_by_count":31,"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":"2505.03005","title":"RADLADS: Rapid Attention Distillation to Linear Attention Decoders at Scale","created":"2025-05-05","cited_by_count":24,"area":null},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23,"area":null},{"id":"2507.02782","title":"Understanding and Improving Length Generalization in Recurrent Models","created":"2025-07-03","cited_by_count":23,"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":"2405.15214","title":"PointRWKV: Efficient RWKV-Like Model for Hierarchical Point Cloud Learning","created":"2024-05-24","cited_by_count":21,"area":null},{"id":"2512.20569","title":"Distilling to Hybrid Attention Models via KL-Guided Layer Selection","created":"2025-12-23","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":"2503.13427","title":"xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference","created":"2025-03-17","cited_by_count":18,"area":null},{"id":"2602.24281","title":"Memory Caching: RNNs with Growing Memory","created":"2026-02-27","cited_by_count":15,"area":null},{"id":"2602.21204","title":"Test-Time Training with KV Binding Is Secretly Linear Attention","created":"2026-02-24","cited_by_count":13,"area":null},{"id":"2504.04308","title":"Gating is Weighting: Understanding Gated Linear Attention through In-context Learning","created":"2025-04-06","cited_by_count":12,"area":null},{"id":"2504.14582","title":"NTIRE 2025 Challenge on Image Super-Resolution (x4): Methods and Results","created":"2025-04-20","cited_by_count":12,"area":null},{"id":"2505.23666","title":"LoLA: Low-Rank Linear Attention With Sparse Caching","created":"2025-05-29","cited_by_count":12,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2405.14930","title":"AstroPT: Scaling Large Observation Models for Astronomy","created":"2024-05-23","cited_by_count":9,"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":"2409.19987","title":"OccRWKV: Rethinking Efficient 3D Semantic Occupancy Prediction with Linear Complexity","created":"2024-09-30","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":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2508.19029","title":"Revisiting associative recall in modern recurrent models","created":"2025-08-26","cited_by_count":8,"area":null},{"id":"2511.07343","title":"TNT: Improving Chunkwise Training for Test-Time Memorization","created":"2025-11-10","cited_by_count":8,"area":null},{"id":"2409.15371","title":"MiSS: Revisiting the Trade-off in LoRA with an Efficient Shard-Sharing Structure","created":"2024-09-19","cited_by_count":7,"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":"2412.14847","title":"A Survey of RWKV","created":"2024-12-19","cited_by_count":6,"area":null},{"id":"2504.21463","title":"RWKV-X: A Linear Complexity Hybrid Language Model","created":"2025-04-30","cited_by_count":6,"area":null},{"id":"2409.00055","title":"SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2502.09172","title":"LOB-Bench: Benchmarking Generative AI for Finance -- an Application to Limit Order Book Data","created":"2025-02-13","cited_by_count":5,"area":null},{"id":"2503.22913","title":"Resona: Improving Context Copying in Linear Recurrence Models with Retrieval","created":"2025-03-28","cited_by_count":5,"area":null},{"id":"2504.06949","title":"Adaptive Computation Pruning for the Forgetting Transformer","created":"2025-04-09","cited_by_count":5,"area":null},{"id":"2410.17477","title":"Do Robot Snakes Dream like Electric Sheep? Investigating the Effects of Architectural Inductive Biases on Hallucination","created":"2024-10-22","cited_by_count":4,"area":null},{"id":"2411.05636","title":"Video RWKV:Video Action Recognition Based RWKV","created":"2024-11-08","cited_by_count":4,"area":null},{"id":"2502.05869","title":"HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition","created":"2025-02-09","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":"2505.03803","title":"RWKVQuant: Quantizing the RWKV Family with Proxy Guided Hybrid of Scalar and Vector Quantization","created":"2025-05-02","cited_by_count":4,"area":null},{"id":"2506.04956","title":"FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2510.01450","title":"Local Linear Attention: An Optimal Interpolation of Linear and Softmax Attention For Test-Time Regression","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2602.02180","title":"STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2603.19606","title":"Beyond Quadratic: Linear-Time Change Detection with RWKV","created":"2026-03-20","cited_by_count":4,"area":null},{"id":"2603.23032","title":"Generative Event Pretraining with Foundation Model Alignment","created":"2026-03-24","cited_by_count":4,"area":null},{"id":"2607.25380","title":"Memory for Large Language Models","created":"2026-07-28","cited_by_count":4,"area":null},{"id":"2410.11687","title":"Learning in the Recurrent State: Gradient Descent with Linear Recurrent Networks","created":"2024-10-15","cited_by_count":3,"area":null},{"id":"2412.03814","title":"Exploring Real&Synthetic Dataset and Linear Attention in Image Restoration","created":"2024-12-05","cited_by_count":3,"area":null},{"id":"2603.15590","title":"Effective Distillation to Hybrid xLSTM Architectures","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2409.00286","title":"OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters","created":"2024-08-30","cited_by_count":2,"area":null},{"id":"2505.11165","title":"Maximizing Asynchronicity in Event-based Neural Networks","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2507.03184","title":"EvRWKV: A Continuous Interactive RWKV Framework for Effective Event-Guided Low-Light Image Enhancement","created":"2025-07-01","cited_by_count":2,"area":null},{"id":"2510.26083","title":"Nirvana: A Specialized Generalist Model With Task-Aware Memory Mechanism","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2510.27258","title":"Higher-order Linear Attention","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2512.08161","title":"Fourier-RWKV: A Multi-State Perception Network for Efficient Image Dehazing","created":"2025-12-09","cited_by_count":2,"area":null},{"id":"2602.22479","title":"Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2604.10946","title":"Learning to Adapt: In-Context Learning Beyond Stationarity","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2606.23670","title":"Tapered Language Models","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2410.23320","title":"Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis","created":"2024-10-30","cited_by_count":1,"area":null},{"id":"2411.02795","title":"The Evolution of RWKV: Advancements in Efficient Language Modeling","created":"2024-11-05","cited_by_count":1,"area":null},{"id":"2412.10856","title":"RWKV-edge: Deeply Compressed RWKV for Resource-Constrained Devices","created":"2024-12-14","cited_by_count":1,"area":null},{"id":"2502.20852","title":"Delta-WKV: A Novel Meta-in-Context Learner for MRI Super-Resolution","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2503.22223","title":"DREMnet: An Interpretable Denoising Framework for Semi-Airborne Transient Electromagnetic Signal","created":"2025-03-28","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":"2507.19353","title":"Smooth Reading: Bridging the Gap of Recurrent LLM to Self-Attention LLM on Long-Context Tasks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.06309","title":"Matrix-Driven Identification and Reconstruction of LLM Weight Homology","created":"2025-08-08","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":"2511.00989","title":"Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis","created":"2025-11-02","cited_by_count":1,"area":null},{"id":"2603.19567","title":"Efficiency Follows Global-Local Decoupling","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2603.22325","title":"Hybrid Associative Memories","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2605.05066","title":"The Impossibility Triangle of Long-Context Modeling","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.13473","title":"OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2605.21070","title":"Towards Understanding Self-Pretraining for Sequence Classification","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2608.16844","title":"Proteus: Incremental Memory Activation for Long-Context Sequence Modeling","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2412.10730","title":"MAL: Cluster-Masked and Multi-Task Pretraining for Enhanced xLSTM Vision Performance","created":"2024-12-14","cited_by_count":0,"area":null},{"id":"2501.01460","title":"GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution","created":"2024-12-31","cited_by_count":0,"area":null},{"id":"2502.00404","title":"Exploring Linear Attention Alternative for Single Image Super-Resolution","created":"2025-02-01","cited_by_count":0,"area":null},{"id":"2505.18522","title":"How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation","created":"2025-05-24","cited_by_count":0,"area":null},{"id":"2506.19761","title":"Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR","created":"2025-06-24","cited_by_count":0,"area":null},{"id":"2508.08289","title":"Attention as Conditioning: What Classical Learning Theory Predicts About Linear Transformers","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2510.02361","title":"ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference","created":"2025-09-28","cited_by_count":0,"area":null},{"id":"2511.06741","title":"Otter: Mitigating Background Distractions of Wide-Angle Few-Shot Action Recognition with Enhanced RWKV","created":"2025-11-10","cited_by_count":0,"area":null},{"id":"2604.05030","title":"Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2604.19826","title":"Co-Located Tests, Better AI Code: How Test Syntax Structure Affects Foundation Model Code Generation","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.06946","title":"Adaptive Memory Decay for Log-Linear Attention","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.31163","title":"Memory by Design: Bayesian Layers for Sequence Modeling","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.19835","title":"Neural Events: Discrete Asynchronous Autoencoders for Event-Based Vision","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20999","title":"Inductive Generalization for Robotic Manipulation","created":"2026-06-19","cited_by_count":0,"area":null}],"next_cursor":"100"}