{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/autoregressive-pretraining-with-mamba-in","title":"Autoregressive Pretraining with Mamba in Vision","arxiv_id":"2406.07537","date":"2024-06-11","proceeding":null,"authors":["Sucheng Ren","Xianhang Li","Haoqin Tu","Feng Wang","Fangxun Shu","Lei Zhang","Jieru Mei","Linjie Yang","Peng Wang","Heng Wang","Alan Yuille","Cihang Xie"],"abstract":"The vision community has started to build with the recently developed state space model, Mamba, as the new backbone for a range of tasks. This paper shows that Mamba's visual capability can be significantly enhanced through autoregressive pretraining, a direction not previously explored. Efficiency-wise, the autoregressive nature can well capitalize on the Mamba's unidirectional recurrent structure, enabling faster overall training speed compared to other training strategies like mask modeling. Performance-wise, autoregressive pretraining equips the Mamba architecture with markedly higher accuracy over its supervised-trained counterparts and, more importantly, successfully unlocks its scaling potential to large and even huge model sizes. For example, with autoregressive pretraining, a base-size Mamba attains 83.2\\% ImageNet accuracy, outperforming its supervised counterpart by 2.0\\%; our huge-size Mamba, the largest Vision Mamba to date, attains 85.0\\% ImageNet accuracy (85.5\\% when finetuned with $384\\times384$ inputs), notably surpassing all other Mamba variants in vision. The code is available at \\url{https://github.com/OliverRensu/ARM}.","url_abs":"https://arxiv.org/abs/2406.07537v1","url_pdf":"https://arxiv.org/pdf/2406.07537v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"autoregressive-pretraining-with-mamba-in","repo_url":"https://github.com/oliverrensu/arm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.07537","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.07537"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/oliverrensu/arm","reach":{"status":"ok"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"affa54d3baff9b37","entry":"build_dataset","repo":"oliverrensu/arm","repo_kind":"official","path":"Finetuning/util/datasets.py","file_url":"https://github.com/oliverrensu/arm/blob/HEAD/Finetuning/util/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"affa54d3baff9b37"}},{"code_sha256_prefix":"d24d1a3d833e4faf","entry":"build_transform","repo":"oliverrensu/arm","repo_kind":"official","path":"Finetuning/util/datasets.py","file_url":"https://github.com/oliverrensu/arm/blob/HEAD/Finetuning/util/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d24d1a3d833e4faf"}},{"code_sha256_prefix":"eb92a366c8f04e0b","entry":"get_layer_id_for_vit","repo":"oliverrensu/arm","repo_kind":"official","path":"Finetuning/util/lr_decay.py","file_url":"https://github.com/oliverrensu/arm/blob/HEAD/Finetuning/util/lr_decay.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb92a366c8f04e0b"}},{"code_sha256_prefix":"527f0d1b1937b52f","entry":"param_groups_lrd","repo":"oliverrensu/arm","repo_kind":"official","path":"Finetuning/util/lr_decay.py","file_url":"https://github.com/oliverrensu/arm/blob/HEAD/Finetuning/util/lr_decay.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"527f0d1b1937b52f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}