{"total":20,"rows":[{"id":"2404.11018","title":"Many-Shot In-Context Learning","created":"2024-04-17","cited_by_count":206,"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":"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":"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":"2405.17381","title":"Various Lengths, Constant Speed: Efficient Language Modeling with Lightning Attention","created":"2024-05-27","cited_by_count":31,"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":"2312.01990","title":"SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust Attention","created":"2023-12-04","cited_by_count":20,"area":null},{"id":"2403.19928","title":"DiJiang: Efficient Large Language Models through Compact Kernelization","created":"2024-03-29","cited_by_count":16,"area":null},{"id":"2404.02882","title":"Linear Attention Sequence Parallelism","created":"2024-04-03","cited_by_count":8,"area":null},{"id":"2403.02920","title":"TaylorShift: Shifting the Complexity of Self-Attention from Squared to Linear (and Back) using Taylor-Softmax","created":"2024-03-05","cited_by_count":7,"area":null},{"id":"2312.11135","title":"Linear Attention via Orthogonal Memory","created":"2023-12-18","cited_by_count":4,"area":null},{"id":"2306.15799","title":"FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2306.00392","title":"Coneheads: Hierarchy Aware Attention","created":"2023-06-01","cited_by_count":1,"area":null},{"id":"2402.17507","title":"Interactive Multi-Head Self-Attention with Linear Complexity","created":"2024-02-27","cited_by_count":1,"area":null},{"id":"2511.00576","title":"FlashEVA: Accelerating LLM inference via Efficient Attention","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2506.09101","title":"Feature Shift Localization Network","created":"2025-06-10","cited_by_count":0,"area":null},{"id":"2512.20562","title":"Shallow Neural Networks Learn Low-Degree Spherical Polynomials with Feature Learning by Learnable Channel Attention","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2603.04127","title":"Data-Aware Random Feature Kernel for Transformers","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2606.31421","title":"Temporal Preservation over Processing: Diagnosing and Designing Spatiotemporal Single-Stage Video Detectors","created":"2026-06-30","cited_by_count":0,"area":null}],"next_cursor":null}