SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.10012 · NeurIPS · 2024

NARAIM: Native Aspect Ratio Autoregressive Image Models

Phillip Lippe, Efstratios Gavves, Samuele Papa, Daniel Gallo Fernández, Rȃzvan-Andrei Matişan, Janusz Partyka, Robert Van Der Klis

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (8 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 8 have no contract verdict; 1 failure of our instrument; 1 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/2410.10012.json · badge: /api/ran/2410.10012.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
daniel-gallo/naraim canonical (classifier label)
classifier basis: classifier_2025
11 ran · 1 no recorded run
FunctionStatusWhere it lives
AttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("50b85435f664a2d6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

InitialProjection Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("6264c3925347e183")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

PositionalEncoding Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("a2d3d013b3d86f43")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

PretrainingHead Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("1c6cca3406b133a4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

PretrainingModel Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("fd5cd486d9a742a5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

ResidualBlock Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("056699efe24f7184")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

Transformer Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("e78dd5d7dc066e2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

TransformerLayer Ran
ran on a synthesized input · constructed an object; no result was computed
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("cdf9a7e7270191af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

dot_product_attention Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("d1eecbe4982a95d1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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_1d_positional_embedding Ran
ran, honoured the contract we drafted
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("89fec47dc1153c22")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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_2d_positional_embedding Ran
ran, honoured the contract we drafted
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("e041d3c8657e8b66")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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.

FractionalPositionalEncoding Not yet run
unverified (harvested, no recorded run)
daniel-gallo/naraim/model/pretraining.py
pointer only (licence: NONE) · get_code("4e313789e5fff393")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, daniel-gallo/naraim 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. No invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 12 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.

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

While vision transformers are able to solve a wide variety of computer vision tasks, no pre-training method has yet demonstrated the same scaling laws as observed in language models. Autoregressive models show promising results, but are commonly trained on images that are cropped or transformed into square images, which distorts or destroys information present in the input. To overcome this limitation, we propose NARAIM, a vision model pre-trained with an autoregressive objective that uses images in their native aspect ratio. By maintaining the native aspect ratio, we preserve the original spatial context, thereby enhancing the model's ability to interpret visual information. In our experiments, we show that maintaining the aspect ratio improves performance on a downstream classification task.

For agents

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

get_harvested_code_for_paper("2410.10012")
get_code_for_paper("2410.10012")
have("2410.10012")

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

curl https://syntology.ai/api/ran/2410.10012.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.10012.svg)](https://syntology.ai/paper/2410.10012)

Connect an agent — have() is free.