Papers › Scalable Pre-training of Large Autoregressive Image Models

Scalable Pre-training of Large Autoregressive Image Models

16 Jan 2024arXiv:2401.08541archive 2025-07-28

Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai, Miguel Angel Bautista, Alexander Toshev, Vaishaal Shankar, Joshua M Susskind, Armand Joulin

This paper introduces AIM, a collection of vision models pre-trained with an autoregressive objective. These models are inspired by their textual counterparts, i.e., Large Language Models (LLMs), and exhibit similar scaling properties. Specifically, we highlight two key findings: (1) the performance of the visual features scale with both the model capacity and the quantity of data, (2) the value of the objective function correlates with the performance of the model on downstream tasks. We illustrate the practical implication of these findings by pre-training a 7 billion parameter AIM on 2 billion images, that achieves 84.0% on ImageNet-1k with a frozen trunk. Interestingly, even at this scale, we observe no sign of saturation in performance, suggesting that AIM potentially represents a new frontier for training large-scale vision models. The pre-training of AIM is similar to the pre-training of LLMs, and does not require any image-specific strategy to stabilize the training at scale.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page 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):

Code

apple/ml-aim officialmentioned in papermentioned on GitHubjaxNOASSERTIONSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Multimodal Autoregressive Pre-training of Large Vision Encoders (arXiv:2411.14402; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
lightly-ai/lightly mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Momentum Contrast for Unsupervised Visual Representation Learning (arXiv:1911.05722; that paper's own run record: 28 ran (of which 16 constructed an object rather than computing a result; 23 with no instrument failure: 0 honoured, 0 violated, 23 with no contract checked; 5 where Syntology's instrument failed) · 14 unverified), A Simple Framework for Contrastive Learning of Visual Representations (arXiv:2002.05709; that paper's own run record: 115 ran (of which 33 constructed an object rather than computing a result; 89 with no instrument failure: 1 honoured, 1 violated, 87 with no contract checked; 26 where Syntology's instrument failed) · 22 unverified), Unsupervised Learning of Visual Features by Contrasting Cluster Assignments (arXiv:2006.09882; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified) and 8 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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.

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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Classification ImageNet AIM-7B Top 1 Accuracy 84.0 #362 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.

Methods

AttentionDense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSoftmaxVision Transformer

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