{"total":60,"rows":[{"id":"2412.06464","title":"Gated Delta Networks: Improving Mamba2 with Delta Rule","created":"2024-12-09","cited_by_count":532,"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":"2506.05233","title":"MesaNet: Sequence Modeling by Locally Optimal Test-Time Training","created":"2025-06-05","cited_by_count":47,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"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":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33,"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":"2507.19595","title":"Efficient Attention Mechanisms for Large Language Models: A Survey","created":"2025-07-25","cited_by_count":22,"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":"2505.17761","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","created":"2025-05-23","cited_by_count":18,"area":null},{"id":"2601.22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","created":"2026-01-29","cited_by_count":18,"area":null},{"id":"2504.18574","title":"Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism","created":"2025-04-22","cited_by_count":15,"area":null},{"id":"2506.02475","title":"Comba: Improving Bilinear RNNs with Closed-loop Control","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2507.16577","title":"Scaling Linear Attention with Sparse State Expansion","created":"2025-07-22","cited_by_count":13,"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":"2510.07318","title":"Artificial Hippocampus Networks for Efficient Long-Context Modeling","created":"2025-10-08","cited_by_count":11,"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":"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":"2505.09193","title":"BiECVC: Gated Diversification of Bidirectional Contexts for Learned Video Compression","created":"2025-05-14","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":"2603.15330","title":"MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2501.16085","title":"ARFlow: Autoregressive Flow with Hybrid Linear Attention","created":"2025-01-27","cited_by_count":7,"area":null},{"id":"2507.10178","title":"Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2607.02303","title":"A Hippocampus for Linear Attention: An Exact Memory for What the Recurrent State Forgets","created":"2026-07-02","cited_by_count":6,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"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":"2509.05276","title":"SpikingBrain: Spiking Brain-inspired Large Models","created":"2025-09-05","cited_by_count":5,"area":null},{"id":"2512.23852","title":"Trellis: Learning to Compress Key-Value Memory in Attention Models","created":"2025-12-29","cited_by_count":5,"area":null},{"id":"2602.01766","title":"CoMeT: Collaborative Memory Transformer for Efficient Long Context Modeling","created":"2026-02-02","cited_by_count":5,"area":null},{"id":"2507.07694","title":"SAS: Simulated Attention Score","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2605.05838","title":"MDN: Parallelizing Stepwise Momentum for Delta Linear Attention","created":"2026-05-07","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":"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":"2602.02047","title":"Dissecting Outlier Dynamics in LLM NVFP4 Pretraining","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2602.12601","title":"HyperMLP: An Integrated Perspective for Sequence Modeling","created":"2026-02-13","cited_by_count":3,"area":null},{"id":"2602.11958","title":"RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.19290","title":"Neural Dynamics Self-Attention for Spiking Transformers","created":"2026-03-09","cited_by_count":2,"area":null},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2606.30562","title":"Morphing into Hybrid Attention Models","created":"2026-06-29","cited_by_count":2,"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":"2602.10410","title":"LUCID: Attention with Preconditioned Representations","created":"2026-02-11","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":"2508.11921","title":"ENA: Efficient N-dimensional Attention","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2512.02685","title":"Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidance","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2601.22630","title":"LINA: Linear Autoregressive Image Generative Models with Continuous Tokens","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.10796","title":"PRISM: Parallel Residual Iterative Sequence Model","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.14702","title":"Gating Enables Curvature: A Geometric Expressivity Gap in Attention","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.28507","title":"Universal Time Series Generation with Neural Controlled Differential Equations","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2609.24417","title":"ARM: Attention with Routed-Memory for Learnable Sparse Control","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.32114","title":"Empowering Hybrid Attention Models on NPUs","created":"2026-09-26","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},{"id":"2609.36529","title":"Triadic Linear Attention: Three-Dimensional Recurrent States for Long-Context Sequence Modeling","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02816","title":"Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.17191","title":"FreeSolo: Linear-time Sparse Attention with Zero-Shot Length Extrapolation","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19257","title":"Long-horizon Video Generation with Slot Memory Addressed By Region Tokens","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}