SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.07537 · 2024

Autoregressive Pretraining with Mamba in Vision

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2406.07537.json · badge: /api/ran/2406.07537.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
oliverrensu/arm canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
build_dataset Ran
ran; our contract draft was wrong, not the code
oliverrensu/arm/Finetuning/util/datasets.py
pointer only (licence: NONE) · get_code("affa54d3baff9b37")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/arm 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.

build_transform Ran
ran; our contract draft was wrong, not the code
oliverrensu/arm/Finetuning/util/datasets.py
pointer only (licence: NONE) · get_code("d24d1a3d833e4faf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/arm 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.

get_layer_id_for_vit Ran
ran, honoured the contract we drafted
oliverrensu/arm/Finetuning/util/lr_decay.py
pointer only (licence: NONE) · get_code("eb92a366c8f04e0b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/arm 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.

param_groups_lrd Ran
ran; our contract draft was wrong, not the code
oliverrensu/arm/Finetuning/util/lr_decay.py
pointer only (licence: NONE) · get_code("527f0d1b1937b52f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, oliverrensu/arm 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.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 1 later) and 3 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
build_dataset 14 other papers
9 dated earlier, 1 the same month, 4 later
2205.03892 (2022-05)
ConvMAE: Masked Convolution Meets Masked Autoencoders
2210.00788 (2022-10)
Towards a Unified View on Visual Parameter-Efficient Transfer Learning
aaai_25300 (2023 (year only))
Exploring Stochastic Autoregressive Image Modeling for Visual Representation
and 11 more not named here

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

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}.

For agents

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

get_harvested_code_for_paper("2406.07537")
get_code_for_paper("2406.07537")
have("2406.07537")

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

curl https://syntology.ai/api/ran/2406.07537.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.07537.svg)](https://syntology.ai/paper/2406.07537)

Connect an agent — have() is free.