{"total":35,"rows":[{"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":"2405.05254","title":"You Only Cache Once: Decoder-Decoder Architectures for Language Models","created":"2024-05-08","cited_by_count":144,"area":null},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127,"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":"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":"2503.02130","title":"Forgetting Transformer: Softmax Attention with a Forget Gate","created":"2025-03-03","cited_by_count":53,"area":null},{"id":"2506.04761","title":"Log-Linear Attention","created":"2025-06-05","cited_by_count":40,"area":null},{"id":"2410.01201","title":"Were RNNs All We Needed?","created":"2024-10-02","cited_by_count":38,"area":null},{"id":"2405.15731","title":"Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks","created":"2024-05-24","cited_by_count":26,"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":"2411.10741","title":"MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map","created":"2024-11-16","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":"2402.00854","title":"SymbolicAI: A framework for logic-based approaches combining generative models and solvers","created":"2024-02-01","cited_by_count":16,"area":null},{"id":"2411.12892","title":"Selective Attention: Enhancing Transformer through Principled Context Control","created":"2024-11-19","cited_by_count":16,"area":null},{"id":"2408.04093","title":"Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters","created":"2024-08-07","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":"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":"2404.02882","title":"Linear Attention Sequence Parallelism","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2405.17383","title":"Unlocking the Secrets of Linear Complexity Sequence Model from A Unified Perspective","created":"2024-05-27","cited_by_count":6,"area":null},{"id":"2502.16249","title":"Linear Attention for Efficient Bidirectional Sequence Modeling","created":"2025-02-22","cited_by_count":4,"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":"2501.13230","title":"Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions","created":"2025-01-22","cited_by_count":2,"area":null},{"id":"2503.11224","title":"Technologies on Effectiveness and Efficiency: A Survey of State Spaces Models","created":"2025-03-14","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":"2404.05843","title":"Softmax Attention with Constant Cost per Token","created":"2024-04-08","cited_by_count":1,"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":"2605.08587","title":"Kaczmarz Linear Attention","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2609.36062","title":"SMat-Attention: Structured Long-Context Sequence Modeling","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2503.03269","title":"Conformal Transformations for Symmetric Power Transformers","created":"2025-03-05","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":"2604.05030","title":"Phase-Associative Memory: Sequence Modeling in Complex Hilbert Space","created":"2026-04-06","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":"2609.39082","title":"Shared Phase and Retention Control for Efficient Adaptive Spectral Recurrence","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}