Papers › Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction

3 Apr 2024arXiv:2404.02905archive 2025-07-28

Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, LiWei Wang

We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and generalize well: VAR, for the first time, makes GPT-like AR models surpass diffusion transformers in image generation. On ImageNet 256x256 benchmark, VAR significantly improve AR baseline by improving Frechet inception distance (FID) from 18.65 to 1.73, inception score (IS) from 80.4 to 350.2, with around 20x faster inference speed. It is also empirically verified that VAR outperforms the Diffusion Transformer (DiT) in multiple dimensions including image quality, inference speed, data efficiency, and scalability. Scaling up VAR models exhibits clear power-law scaling laws similar to those observed in LLMs, with linear correlation coefficients near -0.998 as solid evidence. VAR further showcases zero-shot generalization ability in downstream tasks including image in-painting, out-painting, and editing. These results suggest VAR has initially emulated the two important properties of LLMs: Scaling Laws and zero-shot task generalization. We have released all models and codes to promote the exploration of AR/VAR models for visual generation and unified learning.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also 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

No sample from the archive's official repository (FoundationVision/VAR) is linked to this paper; the 11 samples below come from 2 community repositories. Syntology harvested code from FoundationVision/VAR for another paper.

FoundationVision/VAR: Syntology's graph links these samples to Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (arXiv:2412.04431; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method.

Syntology 11 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 11 samples from 2 repositories, 7 ran (2 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 7 samples that ran has no recorded date.

FoundationVision/VAR officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis (arXiv:2412.04431; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
EkaterinaXie/LiteVAR mentioned on GitHubpytorchMITSyntology: 8 samples, 4 ran (2 instrument-failed) · 4 unverified report
FoundationVision/Infinity mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · our draft was wrong
2ran; the contract check could not run
2ran
4unverified

Licence: 0 of the 11 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

EkaterinaXie/LiteVAR community (archive-listed) 8 samples, 4 ran (2 instrument-failed) · 4 unverified
Normalize in 154 papers models/basic_vae.py ran · our draft was wrong MIT (permissive) · 9fcdaa6e423e8aa7 · report fixture: signature in_channels:int/0/int, num_groups:int/0/int · returned GroupNorm · level recorded 2026-09-22
allgather in 9 papers dist.py ran fingerprinted MIT (permissive) · e847ee15f089dee6 · report fixture: signature t:Tensor/2/float, cat:bool/0/bool · returned Tensor · level recorded 2026-09-26
nonlinearity in 140 papers
census: 4 implementations from 11 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models/basic_vae.py ran · our draft was wrong fingerprinted MIT (permissive) · 3137073275f8c21a · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
should_replace demo_sample_batch_quant.py ran MIT (permissive) · 3c57a99a764d06f2 · report fixture: signature name:str/0/str · returned bool · level recorded 2026-09-25
allreduce in 12 papers dist.py unverified MIT (permissive) · ff4c548fd07140d0 · report
make_attn in 22 papers models/basic_vae.py unverified MIT (permissive) · 793c7e2489dd8dfc · report
new_group in 14 papers dist.py unverified MIT (permissive) · 826ea3fc406a6a09 · report
slow_attn_ban_mini_token_2 models/ban_all_1.py unverified MIT (permissive) · 577a75b98b013aed · report
FoundationVision/Infinity community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
get_params_num in 6 papers infinity/models/infinity.py ran · our draft was wrong MIT (permissive) · 6a19741de3a68058 · report fixture: signature d:int/0/int, w:int/0/int, mlp:int/0/int · returned str · level recorded 2026-09-22
sample_with_top_k_top_p_also_inplace_modifying_logits_ in 6 papers infinity/models/infinity.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 9526ce09c7148703 · report fixture: signature logits_BlV:Tensor/3/float, top_k:int/0/int, top_p:float/0/float, rng:Generator/0/?, num_samples:int/0/int · returned Tensor · level recorded 2026-09-22
sampling_with_top_k_top_p_also_inplace_modifying_probs_ in 5 papers infinity/models/infinity.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 5451c3f14c7e520c · report fixture: signature probs_BlV:Tensor/3/float, top_k:int/0/int, top_p:float/0/float, rng:Generator/0/?, num_samples:int/0/int · returned Tensor · level recorded 2026-09-22

Tasks

Image GenerationImage ReconstructionLanguage ModellingLarge Language ModelZero-shot Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 VAR (Visual Autoregressive) FID 1.73 #37 of 94 Archive leaderboard report
Image Reconstruction Ultra-High Resolution Image Reconstruction Benchmark VAR (16x16) PSNR 21.79 #6 of 6 Archive leaderboard report
Image Reconstruction Ultra-High Resolution Image Reconstruction Benchmark VAR (16x16) rFID 9.85 #6 of 6 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

Absolute Position EncodingsAdamAdaptive Instance NormalizationAttentionDiffusionGPTGPT-2Label SmoothingLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionTransformerVQ-VAE

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