Papers › VMamba: Visual State Space Model
VMamba: Visual State Space Model
Yue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu, Lingxi Xie, YaoWei Wang, Qixiang Ye, Jianbin Jiao, Yunfan Liu
Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module. By traversing along four scanning routes, SS2D bridges the gap between the ordered nature of 1D selective scan and the non-sequential structure of 2D vision data, which facilitates the collection of contextual information from various sources and perspectives. Based on the VSS blocks, we develop a family of VMamba architectures and accelerate them through a succession of architectural and implementation enhancements. Extensive experiments demonstrate VMamba's promising performance across diverse visual perception tasks, highlighting its superior input scaling efficiency compared to existing benchmark models. Source code is available at https://github.com/MzeroMiko/VMamba.
In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.
Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
For agents, on Syntology's MCP service (how to connect):
get_harvested_code_for_paper(arxiv_id="2401.10166")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2401.10166", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2401.10166")
Code
Syntology 46 code samples harvested from 5 repositories linked to this paper: 32 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 10 where Syntology's instrument failed) · 14 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 7 where the contract check could not run; failures of Syntology's instrument, not of the code.
By repository: official repository: 3 samples from 1 repository, 3 ran (0 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 43 samples from 4 repositories, 29 ran (22 with no instrument failure; 7 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
No sample is linked to this paper from 6 of its repositories that Syntology harvested for other papers:
- AmazingDay1/TAME, community (archive-listed): harvested for another paper, listed under the repository
- chenhongruixuan/mambacd, community (archive-listed): harvested for another paper, listed under the repository
- hunto/localmamba, community (archive-listed): harvested for another paper, listed under the repository
- longshaocong/dgmamba, community (archive-listed): harvested for another paper, listed under the repository
- weitunglin/pixmamba, community (archive-listed): harvested for 2 other papers, listed under the repository
- weiwang31/icemamba, community (archive-listed): harvested for another paper, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 32 samples that ran have no recorded date.
13 repositories listed; official and paper-mentioned ones first.
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.
Code Syntology ran Syntology
46 samples harvested: 32 ran (of which 6 constructed an object rather than computing a result; 22 with no instrument failure: 6 honoured, 1 violated, 15 with no contract checked; 10 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.
Licence: 14 of the 46 samples are pointer only, meaning Syntology does not serve that copy's text. For 14 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.
Harvested from 5 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 3 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.
Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.
Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.
A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
590aaaa7c8644eeb · report
fixture: signature y:Tensor/5/float, in_channel_first:bool/0/bool, out_channel_first:bool/0/bool, scans:int/0/int · returned Tensor · level recorded, date not recorded e95046a63069075a · report
fixture: signature x:Tensor/5/float, in_channel_first:bool/0/bool, out_channel_first:bool/0/bool, scans:int/0/int · returned Tensor · level recorded, date not recorded ee0b8d655d08adf0 · report
fixture: signature x:Tensor/4/float, in_channel_first:bool/0/bool, out_channel_first:bool/0/bool, scans:int/0/int · returned Tensor · level recorded, date not recorded 9a3adc8e6de35ac1 · report
fixture: signature B:int/0/int, L:int/0/int, D:int/0/int, N:int/0/int, with_D:bool/0/bool, with_Z:bool/0/bool, with_complex:bool/0/bool · returned int · level recorded 2026-09-26 4b9af31cf72b3d4a · report
fixture: signature B:int/0/int, L:int/0/int, D:int/0/int, N:int/0/int, with_D:bool/0/bool, with_Z:bool/0/bool, with_Group:bool/0/bool, with_complex:bool/0/bool · returned float · level recorded 2026-09-26 eda8d821a5689bf0 · report
census: 3 implementations from 7 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32 baseline_other/mamba/medmamba.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only ·
057445f270d16a96 · report
fixture: signature x:Tensor/4/float, groups:int/0/int · returned Tensor · level recorded 2026-09-22 f6b944f50d3f15ae · report
fixture: signature model:callable/0/? · returned int · level recorded, date not recorded fe873ee58a22c0f7 · report
fixture: signature num_class:int/0/int · returned DenseNet · level recorded 2026-09-24 census: 27 implementations from 61 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 4, kind float, dtype float32 grad_cam/vit_model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) here; the stored copy is pointer only ·
fe7d4321dbeef661 · report
fixture: signature x:Tensor/4/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-22 2202fd90583e6341 · report
fixture: signature x:Tensor/2/float, drop_prob:float/0/float, training:bool/0/bool · returned Tensor · level recorded 2026-09-26 da1a64838a2535e5 · report
fixture: signature B:int/0/int, L:int/0/int, D:int/0/int, N:int/0/int, with_D:bool/0/bool, with_Z:bool/0/bool, with_complex:bool/0/bool · returned int · level recorded 2026-09-25 0b84e99fd1e93dd6 · report
fixture: signature B:int/0/int, L:int/0/int, D:int/0/int, N:int/0/int, with_D:bool/0/bool, with_Z:bool/0/bool, with_Group:bool/0/bool, with_complex:bool/0/bool · returned float · level recorded 2026-09-25 c00dcf8428ee981b · report
fixture: signature B:int/0/int, L:int/0/int, D:int/0/int, N:int/0/int, with_D:bool/0/bool, with_Z:bool/0/bool, with_Group:bool/0/bool, with_complex:bool/0/bool · returned float · level recorded 2026-09-24 a039eb8f1d0b3354 · report
fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24 4022952e5d693153 · report
fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-25 f9779263c018667b · report
fixture: signature num_classes:int/0/int · returned ResNet · level recorded 2026-09-24 1ddca20292522088 · report
fixture: signature inputs:list/1/MockInput, outputs:NoneType/0/? · returned float · level recorded 2026-09-24 census: 13 implementations from 17 papers, 5 distinct outputs across 3 buckets, one shared input per bucket grad_cam/swin_model.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only ·
1244e2f07fb63623 · report
fixture: signature x:Tensor/4/float, window_size:int/0/int · returned Tensor · level recorded 2026-09-26 d14e0252b43325ae · report
fixture: signature windows:Tensor/4/float, window_size:int/0/int, H:int/0/int, W:int/0/int · returned Tensor · level recorded 2026-09-26 7ac1da235babac9c · report
893b6b88ba8dc50f · report
28a7176a9777c76c · report
146200bf92a1418d · report
1366379c7d284cc9 · report
3dbfd852a172ee6a · report
ab4cbc78e4e78e94 · report
ccec5a35b674c038 · report
fixture: returned Final_PatchExpand2D · level recorded 2026-09-22 79bd4e665fb7cc5c · report
fixture: returned PatchEmbed2D · level recorded 2026-09-22 c9ac9c816177196c · report
fixture: returned PatchExpand2D · level recorded 2026-09-22 d74545ecbd87b7ed · report
fixture: returned PatchMerging2D · level recorded 2026-09-22 722c22ee72b8915d · report
fixture: returned SS2D · level recorded 2026-09-22 70f3d058a09ba16e · report
fixture: returned VSSM · level recorded 2026-09-22 23a1f34627822bb3 · report
fixture: signature name:str/0/str, log_dir:str/0/str · returned Logger · level recorded 2026-09-24 ae1a2dd9d62e7fad · report
fixture: signature config:Config/0/?, model:callable/0/? · returned Adam · level recorded 2026-09-24 dea42821258184c2 · report
fixture: signature config:Config/0/?, optimizer:SGD/0/? · returned CosineAnnealingLR · level recorded 2026-09-24 960b785e65a00358 · report
fixture: signature image:ndarray/2/float, label:ndarray/2/int · returned tuple · level recorded 2026-09-24 43fa66325ce3cafd · report
fixture: signature image:ndarray/2/float, label:ndarray/2/int · returned tuple · level recorded 2026-09-24 4709d469c5e0a024 · report
fixture: signature train_loader:list/1/tuple, model:callable/0/?, criterion:callable/0/?, optimizer:SGD/0/?, scheduler:StepLR/0/?, epoch:int/0/int, step:int/0/int, logger:SimpleLogger/0/?, config:SimpleConfig/0/?, writer:SimpleWriter/0/? · returned int · level recorded 2026-09-24 15d76d94bb1b8c16 · report
fixture: signature test_loader:list/1/tuple, model:callable/0/?, criterion:callable/0/?, epoch:int/0/int, logger:Logger/0/?, config:Config/0/? · returned float64 · level recorded 2026-09-24 Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for VMamba (graph method: VMamba). 9 bricks; individually on a fixture: 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 6 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.
- VSSM entry · level 1 · ran ·
70f3d058a09ba16e - Final_PatchExpand2D model · level 1 · ran ·
ccec5a35b674c038 - PatchEmbed2D model · level 1 · ran ·
79bd4e665fb7cc5c - PatchExpand2D model · level 1 · ran ·
c9ac9c816177196c - PatchMerging2D model · level 1 · ran ·
d74545ecbd87b7ed - VSSLayer model · level 0 · unverified ·
f20d039b90ff3c82 - VSSLayer_up model · level 0 · unverified ·
c452cd03dafb5b1d - VSSBlock model · level 0 · unverified ·
b1a133903e053491 - SS2D model · level 1 · ran ·
722c22ee72b8915d
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2401.10166") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections