{"total":16,"rows":[{"id":"2311.04823","title":"Hierarchically Gated Recurrent Neural Network for Sequence Modeling","created":"2023-11-08","cited_by_count":102,"area":null},{"id":"2210.10340","title":"The Devil in Linear Transformer","created":"2022-10-19","cited_by_count":98,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"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":"2211.13955","title":"MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention","created":"2022-11-25","cited_by_count":20,"area":null},{"id":"2406.16690","title":"Scaling Laws for Linear Complexity Language Models","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2307.09270","title":"Linearized Relative Positional Encoding","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2210.00640","title":"Wide Attention Is The Way Forward For Transformers?","created":"2022-10-02","cited_by_count":8,"area":null},{"id":"2307.10156","title":"Exploring Transformer Extrapolation","created":"2023-07-19","cited_by_count":8,"area":null},{"id":"2210.08164","title":"Linear Video Transformer with Feature Fixation","created":"2022-10-15","cited_by_count":6,"area":null},{"id":"2311.08756","title":"Accelerating Toeplitz Neural Network with Constant-time Inference Complexity","created":"2023-11-15","cited_by_count":6,"area":null},{"id":"2210.00641","title":"DARTFormer: Finding The Best Type Of Attention","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2304.08453","title":"Improving Autoregressive NLP Tasks via Modular Linearized Attention","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2308.02553","title":"Survey on Computer Vision Techniques for Internet-of-Things Devices","created":"2023-08-02","cited_by_count":0,"area":null},{"id":"2502.09503","title":"AttentionSmithy: A Modular Framework for Rapid Transformer Development and Customization","created":"2025-02-13","cited_by_count":0,"area":null}],"next_cursor":null}