Papers › MambaVision: A Hybrid Mamba-Transformer Vision Backbone

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

10 Jul 2024CVPR 2025 1arXiv:2407.08083archive 2025-07-28

Ali Hatamizadeh, Jan Kautz

We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput. In downstream tasks such as object detection, instance segmentation, and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably sized backbones while demonstrating favorable performance. Code: https://github.com/NVlabs/MambaVision

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2407.08083")

Code

Syntology Ran 2 of 8 code samples harvested from 2 repositories linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 1 ran with no contract checked.

By repository: official repository: 6 samples from 1 repository, 1 ran; community (archive-listed): 2 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nvlabs/mambavision officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
hashmatshadab/mambarobustness mentioned on GitHubpytorch report
jiaowoguanren0615/MambaVision mentioned on GitHubpytorch report

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.

Code Syntology ran Syntology

8 samples harvested; 2 ran; 0 honoured the contract we drafted; 6 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · fixture could not drive it
1ran
6unverified

Licence: 6 of the 8 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

register_pip_model nvlabs/mambavision/mambavision/models/registry.py official repository ran licence not identified · pointer only · 9774a9d2355fe421 · report
create_scheduler nvlabs/mambavision/mambavision/scheduler/scheduler_factory.py official repository unverified licence not identified · pointer only · 849e053052794bfb · report
is_model nvlabs/mambavision/mambavision/models/registry.py official repository unverified no licence file found · pointer only · cd2a47ded9dd84cf · report
list_models nvlabs/mambavision/mambavision/models/registry.py official repository unverified no licence file found · pointer only · d14a6ca5ff9d530e · report
validate nvlabs/mambavision/mambavision/validate_pip_model.py official repository unverified licence not identified · pointer only · 9ca6ef803df4e229 · report
validate nvlabs/mambavision/mambavision/validate.py official repository unverified licence not identified · pointer only · d432daacdf9484ff · report
window_partition jiaowoguanren0615/MambaVision/models/build_cls_models.py community (archive-listed) ran · fixture could not drive it fingerprinted MIT (permissive) · 88bf73966cf30ec8 · report
window_reverse jiaowoguanren0615/MambaVision/models/build_cls_models.py community (archive-listed) unverified MIT (permissive) · 578f68a6dc6b6dbe · report

Tasks

Image ClassificationInstance SegmentationMambaObject DetectionSemantic Segmentationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet MambaVision-L3 GFLOPs 489.1 #58 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-L3 Top 1 Accuracy 88.1% #58 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-L GFLOPs 34.9 #271 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-L Number of params 227.9M #271 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-L Top 1 Accuracy 85% #271 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-B GFLOPs 15 #343 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-B Number of params 97.7M #343 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-B Top 1 Accuracy 84.2% #343 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-S GFLOPs 7.5 #445 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-S Number of params 50.1M #445 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-S Top 1 Accuracy 83.3% #445 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T2 GFLOPs 5.1 #514 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T2 Number of params 35.1M #514 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T2 Top 1 Accuracy 82.7% #514 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T GFLOPs 4.4 #554 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T Number of params 31.8M #554 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-T Top 1 Accuracy 82.3% #554 of 1060 Archive leaderboard report
Image Classification ImageNet MambaVision-L2 Number of params 241.5M #1057 of 1060 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

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