SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08083 · 2024

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 2 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.08083.json · badge: /api/ran/2407.08083.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
nvlabs/mambavision canonical (classifier label)
classifier basis: census
3 ran · 3 no recorded run
jiaowoguanren0615/MambaVision reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
is_model Ran
ran, violated the contract we drafted
nvlabs/mambavision/mambavision/models/registry.py
pointer only (licence: NONE); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("cd2a47ded9dd84cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nvlabs/mambavision when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

list_models Ran
ran, honoured the contract we drafted
nvlabs/mambavision/mambavision/models/registry.py
pointer only (licence: NONE); the stored copy get_code serves, from Yuzhe-Fu/FlashFPS, is pointer only (licence: NOASSERTION) · get_code("d14a6ca5ff9d530e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, nvlabs/mambavision when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

register_pip_model Ran
ran; our contract draft was wrong, not the code
nvlabs/mambavision/mambavision/models/registry.py
pointer only (licence: NOASSERTION) · get_code("9774a9d2355fe421")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nvlabs/mambavision (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

window_partition Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jiaowoguanren0615/MambaVision/models/build_cls_models.py
code served (permissive licence) · get_code("88bf73966cf30ec8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 3, dtype family float, shape (24, 4, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# Create a small input tensor
# Shape: (B, C, H, W) where B=2, C=4, H=8, W=6
# H and W must be divisible by window_size
x = torch.randn(2, 4, 8, 6)

# Window size must divide both H and W evenly
window_size = 2

ARGS = {
    "x": x,
    "window_size": window_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (24, 4, 4) — shape (24, 4, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
create_scheduler Not yet run
unverified (harvested, no recorded run)
nvlabs/mambavision/mambavision/scheduler/scheduler_factory.py
pointer only (licence: NOASSERTION) · get_code("849e053052794bfb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nvlabs/mambavision (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
nvlabs/mambavision/mambavision/validate_pip_model.py
pointer only (licence: NOASSERTION) · get_code("9ca6ef803df4e229")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nvlabs/mambavision (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
nvlabs/mambavision/mambavision/validate.py
pointer only (licence: NOASSERTION) · get_code("d432daacdf9484ff")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, nvlabs/mambavision (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

window_reverse Not yet run
unverified (harvested, no recorded run)
jiaowoguanren0615/MambaVision/models/build_cls_models.py
code served (permissive licence) · get_code("578f68a6dc6b6dbe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 4 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
is_model 22 other papers
20 dated earlier, 2 later
1409.4842 (2014-09)
Going deeper with convolutions
1512.00567 (2015-12)
Rethinking the Inception Architecture for Computer Vision
1608.06993 (2016-08)
Densely Connected Convolutional Networks
and 19 more not named here
list_models 12 other papers
10 dated earlier, 2 later
2105.01601 (2021-05)
MLP-Mixer: An all-MLP Architecture for Vision
2205.10528 (2022-05)
PointVector: A Vector Representation In Point Cloud Analysis
2206.03452 (2022-06)
Can CNNs Be More Robust Than Transformers?
and 9 more not named here
window_partition 2 other papers
1 dated earlier, 1 later
2306.06189 (2023-06)
FasterViT: Fast Vision Transformers with Hierarchical Attention
2509.21265 (2025-09)
MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation
window_reverse 1 other paper
1 later
2509.21265 (2025-09)
MedVSR: Medical Video Super-Resolution with Cross State-Space Propagation

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.08083")
get_code_for_paper("2407.08083")
have("2407.08083")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.08083.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.08083.svg)](https://syntology.ai/paper/2407.08083)

Connect an agent — have() is free.