--> Computer Science > Machine Learning arXiv:2602.17363 (cs) [Submitted on 19 Feb 2026 ( v1 ), last revised 2 Apr 2026 (this version, v2)] Title: 2Mamba2Furious: Linear in Complexity, Competitive in Accuracy Authors: Gabriel Mongaras , Eric C. Larson View a PDF of the paper titled 2Mamba2Furious: Linear in Complexity, Competitive in Accuracy, by Gabriel Mongaras and 1 other authors View PDF HTML (experimental) Abstract: Linear attention transformers have become a strong alternative to softmax attention due to their efficiency. However, linear attention tends to be less expressive and results in reduced accuracy compared to softmax attention. To bridge the accuracy gap between softmax attention and linear attention, we manipulate Mamba-2, a very strong linear attention variant. We first simplify Mamba-2 down to its most fundamental and important components, evaluating which specific choices make it most accurate. From this simplified Mamba variant (Mamba-2S), we improve the A-mask and increase the order of the hidden state, resulting in a method, which we call 2Mamba, that is nearly as accurate as softmax attention, yet much more memory efficient for long context lengths. We also investigate elements to Mamba-2 that help surpass softmax attention accuracy. Code is provided for all our experiments Subjects: Machine Learning (cs.LG) ACM classes: I.2; I.2.6 Cite as: arXiv:2602.17363 [cs.LG] (or arXiv:2602.17363v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2602.17363 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Gabriel Mongaras [ view email ] [v1] Thu, 19 Feb 2026 13:45:23 UTC (8,567 KB) [v2] Thu, 2 Apr 2026 02:07:56 UTC (20,578 KB) Full-text links: Access Paper: View a PDF of the paper titled 2Mamba2Furious: Linear in Complexity, Competitive in Accuracy, by Gabriel Mongaras and 1 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-02 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation &times; loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? )