{"url":"/task/long-range-modeling","name":"Long-range modeling","slug":"long-range-modeling","description_markdown":"A new task for testing the long-sequence modeling capabilities and efficiency of language models.\r\n\r\nImage credit: [SCROLLS: Standardized CompaRison Over Long Language Sequences](https://arxiv.org/pdf/2201.03533v1.pdf)","categories":[{"name":"Medical","url":"/area/medical"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":95,"papers_with_code":69,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/long-range-modeling-on-scrolls","slug":"long-range-modeling-on-scrolls","dataset":"SCROLLS","dataset_url":"/dataset/scrolls","rows_in_archive":13,"metrics":["Avg.","GovRep","SumScr","QMSum","Qspr","Nrtv","QALT EM-T/H","CNLI"],"first_row_in_archive_order":{"model":"CoLT5 XL","paper_title":"CoLT5: Faster Long-Range Transformers with Conditional Computation","paper_url":"/paper/colt5-faster-long-range-transformers-with","paper_date":"2023-03-17","arxiv_id":"2303.09752","code_links":[],"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}}},{"leaderboard":"/sota/long-range-modeling-on-lra","slug":"long-range-modeling-on-lra","dataset":"LRA","dataset_url":"/dataset/lra","rows_in_archive":7,"metrics":["Avg","Image","ListOps","Pathfinder","Text","Retrieval","Pathfinder-X"],"first_row_in_archive_order":{"model":"S5","paper_title":"Simplified State Space Layers for Sequence Modeling","paper_url":"/paper/simplified-state-space-layers-for-sequence","paper_date":"2022-08-09","arxiv_id":"2208.04933","code_links":[{"title":"lindermanlab/S5","url":"https://github.com/lindermanlab/S5"},{"title":"uzh-rpg/ssms_event_cameras","url":"https://github.com/uzh-rpg/ssms_event_cameras"},{"title":"Efficient-Scalable-Machine-Learning/event-ssm","url":"https://github.com/Efficient-Scalable-Machine-Learning/event-ssm"},{"title":"msgwak/last","url":"https://github.com/msgwak/last"},{"title":"leonty1/essm","url":"https://github.com/leonty1/essm"},{"title":"leonty1/deepldnn","url":"https://github.com/leonty1/deepldnn"}],"syntology":{"n":19,"n_ran":4,"n_unverified":15,"n_pointer_only":3}}}],"datasets":[{"url":"/dataset/lra","name":"LRA","full_name":"Long-Range Arena","num_papers_in_archive":180},{"url":"/dataset/scrolls","name":"SCROLLS","full_name":"Standardized CompaRison Over Long Language Sequences","num_papers_in_archive":42},{"url":"/dataset/muld","name":"MuLD","full_name":"Multitask Long Document Benchmark","num_papers_in_archive":3},{"url":"/dataset/pathfinder-x2","name":"Pathfinder-X2","full_name":"","num_papers_in_archive":0}],"subtasks":[],"parent_tasks":[{"url":"/task/language-modelling","name":"Language Modelling"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":69,"tagged_in_all":95,"items":[{"url":"/paper/mamba-linear-time-sequence-modeling-with","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","date":"2023-12-01","arxiv_id":"2312.00752","repositories_listed":35,"syntology":{"n":62,"n_ran":18,"n_unverified":44,"n_pointer_only":28}},{"url":"/paper/efficiently-modeling-long-sequences-with-1","title":"Efficiently Modeling Long Sequences with Structured State Spaces","date":"2021-10-31","arxiv_id":"2111.00396","repositories_listed":8,"syntology":{"n":55,"n_ran":28,"n_unverified":27,"n_pointer_only":3}},{"url":"/paper/mega-moving-average-equipped-gated-attention","title":"Mega: Moving Average Equipped Gated Attention","date":"2022-09-21","arxiv_id":"2209.10655","repositories_listed":7,"syntology":{"n":13,"n_ran":12,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/simplified-state-space-layers-for-sequence","title":"Simplified State Space Layers for Sequence Modeling","date":"2022-08-09","arxiv_id":"2208.04933","repositories_listed":6,"syntology":{"n":19,"n_ran":4,"n_unverified":15,"n_pointer_only":3}},{"url":"/paper/long-range-arena-a-benchmark-for-efficient-1","title":"Long Range Arena: A Benchmark for Efficient Transformers","date":"2020-11-08","arxiv_id":"2011.04006","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/longt5-efficient-text-to-text-transformer-for","title":"LongT5: Efficient Text-To-Text Transformer for Long Sequences","date":"2021-12-15","arxiv_id":"2112.07916","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/mambaad-exploring-state-space-models-for","title":"MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection","date":"2024-04-09","arxiv_id":"2404.06564","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/hungry-hungry-hippos-towards-language","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","date":"2022-12-28","arxiv_id":"2212.14052","repositories_listed":3,"syntology":{"n":15,"n_ran":7,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/disentangling-and-unifying-graph-convolutions","title":"Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition","date":"2020-03-31","arxiv_id":"2003.14111","repositories_listed":3,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/large-window-based-mamba-unet-for-medical","title":"LKM-UNet: Large Kernel Vision Mamba UNet for Medical Image Segmentation","date":"2024-03-12","arxiv_id":"2403.07332","repositories_listed":2,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":11}},{"url":"/paper/mambamorph-a-mamba-based-backbone-with","title":"MambaMorph: a Mamba-based Framework for Medical MR-CT Deformable Registration","date":"2024-01-25","arxiv_id":"2401.13934","repositories_listed":2,"syntology":null},{"url":"/paper/dimension-mixer-a-generalized-method-for","title":"Dimension Mixer: Group Mixing of Input Dimensions for Efficient Function Approximation","date":"2023-11-30","arxiv_id":"2311.18735","repositories_listed":2,"syntology":null},{"url":"/paper/t-former-an-efficient-transformer-for-image","title":"T-former: An Efficient Transformer for Image Inpainting","date":"2023-05-12","arxiv_id":"2305.07239","repositories_listed":2,"syntology":null},{"url":"/paper/investigating-efficiently-extending","title":"Investigating Efficiently Extending Transformers for Long Input Summarization","date":"2022-08-08","arxiv_id":"2208.04347","repositories_listed":2,"syntology":null},{"url":"/paper/weakly-supervised-object-localization-via","title":"Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration","date":"2022-07-21","arxiv_id":"2207.10447","repositories_listed":2,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/on-the-parameterization-and-initialization-of","title":"On the Parameterization and Initialization of Diagonal State Space Models","date":"2022-06-23","arxiv_id":"2206.11893","repositories_listed":2,"syntology":null},{"url":"/paper/unifying-language-learning-paradigms","title":"UL2: Unifying Language Learning Paradigms","date":"2022-05-10","arxiv_id":"2205.05131","repositories_listed":2,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/paramixer-parameterizing-mixing-links-in","title":"Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better than Dot-Product Self-Attention","date":"2022-04-22","arxiv_id":"2204.10670","repositories_listed":2,"syntology":null},{"url":"/paper/diagonal-state-spaces-are-as-effective-as","title":"Diagonal State Spaces are as Effective as Structured State Spaces","date":"2022-03-27","arxiv_id":"2203.14343","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/scrolls-standardized-comparison-over-long","title":"SCROLLS: Standardized CompaRison Over Long Language Sequences","date":"2022-01-10","arxiv_id":"2201.03533","repositories_listed":2,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/u-rwkv-lightweight-medical-image-segmentation","title":"U-RWKV: Lightweight medical image segmentation with direction-adaptive RWKV","date":"2025-07-15","arxiv_id":"2507.11415","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/mambafusion-height-fidelity-dense-global","title":"MambaFusion: Height-Fidelity Dense Global Fusion for Multi-modal 3D Object Detection","date":"2025-07-06","arxiv_id":"2507.04369","repositories_listed":1,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/cdpdnet-integrating-text-guidance-with-hybrid","title":"CDPDNet: Integrating Text Guidance with Hybrid Vision Encoders for Medical Image Segmentation","date":"2025-05-25","arxiv_id":"2505.18958","repositories_listed":1,"syntology":null},{"url":"/paper/janusdna-a-powerful-bi-directional-hybrid-dna","title":"JanusDNA: A Powerful Bi-directional Hybrid DNA Foundation Model","date":"2025-05-22","arxiv_id":"2505.17257","repositories_listed":1,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/2505-11099","title":"Hybrid-Emba3D: Geometry-Aware and Cross-Path Feature Hybrid Enhanced State Space Model for Point Cloud Classification","date":"2025-05-16","arxiv_id":"2505.11099","repositories_listed":1,"syntology":null},{"url":"/paper/vgamba-attentive-state-space-bottleneck-for","title":"vGamba: Attentive State Space Bottleneck for efficient Long-range Dependencies in Visual Recognition","date":"2025-03-27","arxiv_id":"2503.21262","repositories_listed":1,"syntology":null},{"url":"/paper/vadmamba-exploring-state-space-models-for","title":"VADMamba: Exploring State Space Models for Fast Video Anomaly Detection","date":"2025-03-27","arxiv_id":"2503.21169","repositories_listed":1,"syntology":null},{"url":"/paper/emulating-self-attention-with-convolution-for","title":"Emulating Self-attention with Convolution for Efficient Image Super-Resolution","date":"2025-03-09","arxiv_id":"2503.06671","repositories_listed":1,"syntology":null},{"url":"/paper/km-unet-kan-mamba-unet-for-medical-image","title":"KM-UNet KAN Mamba UNet for medical image segmentation","date":"2025-01-05","arxiv_id":"2501.02559","repositories_listed":1,"syntology":null},{"url":"/paper/giraffe-design-choices-for-extending-the","title":"GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models","date":"2024-12-17","arxiv_id":"2412.12735","repositories_listed":1,"syntology":null}],"syntology_records":17,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}