Papers › Autoregressive Image Generation without Vector Quantization

Autoregressive Image Generation without Vector Quantization

17 Jun 2024arXiv:2406.11838archive 2025-07-28

Tianhong Li, Yonglong Tian, He Li, Mingyang Deng, Kaiming He

Conventional wisdom holds that autoregressive models for image generation are typically accompanied by vector-quantized tokens. We observe that while a discrete-valued space can facilitate representing a categorical distribution, it is not a necessity for autoregressive modeling. In this work, we propose to model the per-token probability distribution using a diffusion procedure, which allows us to apply autoregressive models in a continuous-valued space. Rather than using categorical cross-entropy loss, we define a Diffusion Loss function to model the per-token probability. This approach eliminates the need for discrete-valued tokenizers. We evaluate its effectiveness across a wide range of cases, including standard autoregressive models and generalized masked autoregressive (MAR) variants. By removing vector quantization, our image generator achieves strong results while enjoying the speed advantage of sequence modeling. We hope this work will motivate the use of autoregressive generation in other continuous-valued domains and applications. Code is available at: https://github.com/LTH14/mar.

PaperPDFCodeCode Syntology ranMethod as code

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

Syntology 13 code samples: 12 from 1 repository linked to this paper, 1 identical to code harvested from another paper's repository. Across all 13: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 12 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed); 1 identical to code first harvested elsewhere. 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 8 samples that ran has no recorded date.

lth14/mar officialmentioned in papermentioned on GitHubpytorchSyntology: 12 samples, 7 ran (1 instrument-failed) · 5 unverified report
shaochenze/ear mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Continuous Visual Autoregressive Generation via Score Maximization (arXiv:2505.07812; that paper's own run record: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 4 samples that ran constructed an object rather than computing a result); 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

13 samples harvested: 8 ran (of which 5 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

1ran · honoured contract
2ran; the contract check could not run
5ran
5unverified

Licence: 1 of the 13 samples is 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 lth14/mar. 1 sample is listed last, in a group without a repository. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

lth14/mar official repository 12 samples, 7 ran (1 instrument-failed) · 5 unverified
FinalLayer in 29 papers models/diffloss.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 89c137ff7c13fc84 · report fixture: returned FinalLayer · level recorded 2026-09-22
GaussianDiffusion in 61 papers models/diffloss.py ran MIT (permissive) · de57ba56d49f5ccb · report fixture: returned GaussianDiffusion · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
models/diffloss.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 944b8eccd301a676 · report fixture: returned ResBlock · level recorded 2026-09-22
SimpleMLPAdaLN models/diffloss.py ran · metamorphic tier: deterministic MIT (permissive) · 11f5d9b171f4a6e3 · report fixture: returned SimpleMLPAdaLN · level recorded 2026-09-22
_WrappedModel models/diffloss.py ran MIT (permissive) · 68c1d0608671c310 · report fixture: returned _WrappedModel · level recorded 2026-09-22
_extract_into_tensor in 7 papers models/diffloss.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 086e19314a5cc8b9 · report fixture: signature arr:ndarray/1/float, timesteps:Tensor/1/int, broadcast_shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
modulate in 137 papers
census: 3 implementations from 12 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
models/diffloss.py ran · honoured contract fingerprinted MIT (permissive) · 62fcb3912a967a50 · report fixture: signature x:Tensor/2/float, shift:Tensor/2/float, scale:Tensor/2/float · returned Tensor · level recorded, date not recorded
DiffLoss models/diffloss.py unverified MIT (permissive) · 0b1b4cb568fcf57f · report
ModelVarType models/diffloss.py unverified MIT (permissive) · e58dd85eb8661db5 · report
SpacedDiffusion in 12 papers models/diffloss.py unverified MIT (permissive) · 5f227e2400952f44 · report
create_diffusion models/diffloss.py unverified MIT (permissive) · 2b4d845f9d4a841f · report
mask_by_order in 7 papers models/mar.py unverified MIT (permissive) · d076098d89dd7262 · report
Repository not located 1 sample, 1 ran (1 instrument-failed) · 0 unverified
1 sample is identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
space_timesteps in 72 papers repository not located ran; the contract check could not run (RAISES) · metamorphic tier: deterministic licence of this copy not recorded · ea9dbc131adf582e · report fixture: signature num_timesteps:int/0/int, section_counts:list/1/int · returned set · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Diffusion Loss function (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Diffusion Loss function (graph method: Diffusion Loss function). 16 bricks; individually on a fixture: 10 ran (of which 5 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. DiffLoss entry · level 0 · unverified · 0b1b4cb568fcf57f
  2. SimpleMLPAdaLN model · level 1 · ran · 11f5d9b171f4a6e3
  3. create_diffusion helper · level 0 · unverified · 2b4d845f9d4a841f
  4. FinalLayer helper · level 1 · ran · 89c137ff7c13fc84
  5. ResBlock helper · level 1 · ran · 944b8eccd301a676
  6. TimestepEmbedder helper · level 1 · ran · 36e69cc6393e3e74
  7. SpacedDiffusion helper · level 0 · unverified · 5f227e2400952f44
  8. space_timesteps helper · level 1 · ran; the contract check could not run (RAISES) · ea9dbc131adf582e
  9. modulate helper · level 1 · ran · honoured contract · 62fcb3912a967a50
  10. GaussianDiffusion helper · level 1 · ran · de57ba56d49f5ccb
  11. _WrappedModel helper · level 1 · ran · 68c1d0608671c310
  12. LossType helper · level 0 · unverified · 3dfb2574af178220
  13. ModelMeanType helper · level 0 · unverified · f1e863a92ff43943
  14. ModelVarType helper · level 0 · unverified · e58dd85eb8661db5
  15. _extract_into_tensor helper · level 1 · ran; the contract check could not run (RAISES) · 086e19314a5cc8b9
  16. mean_flat helper · level 1 · ran · our draft was wrong · f6d7c009a8efb8b7

harvested Assembly for Diffusion Loss function (graph method: Diffusion Loss function). 5 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ScoreLoss entry · level 1 · ran · ebb911dced9a386c
  2. SimpleMLPAdaLN model · level 1 · ran · 4cc21af2ea34aa07
  3. FinalLayer model · level 1 · ran · 69746d7a74acca85
  4. ResBlock model · level 1 · ran · 881cc666f6a30277
  5. modulate helper · level 1 · ran · honoured contract · 62fcb3912a967a50

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2406.11838") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image GenerationQuantization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 MAR-H, Diff Loss FID 1.55 #24 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 MAR-L, Diff Loss FID 1.78 #39 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 MAR-B, Diff Loss FID 2.31 #56 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 MAR-L, Diff Loss FID 1.73 #17 of 52 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

DiffusionSPEED

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