Papers › Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

Revisiting Non-Autoregressive Transformers for Efficient Image Synthesis

8 Jun 2024CVPR 2024 1arXiv:2406.05478archive 2025-07-28

Zanlin Ni, Yulin Wang, Renping Zhou, Jiayi Guo, Jinyi Hu, Zhiyuan Liu, Shiji Song, Yuan YAO, Gao Huang

The field of image synthesis is currently flourishing due to the advancements in diffusion models. While diffusion models have been successful, their computational intensity has prompted the pursuit of more efficient alternatives. As a representative work, non-autoregressive Transformers (NATs) have been recognized for their rapid generation. However, a major drawback of these models is their inferior performance compared to diffusion models. In this paper, we aim to re-evaluate the full potential of NATs by revisiting the design of their training and inference strategies. Specifically, we identify the complexities in properly configuring these strategies and indicate the possible sub-optimality in existing heuristic-driven designs. Recognizing this, we propose to go beyond existing methods by directly solving the optimal strategies in an automatic framework. The resulting method, named AutoNAT, advances the performance boundaries of NATs notably, and is able to perform comparably with the latest diffusion models at a significantly reduced inference cost. The effectiveness of AutoNAT is validated on four benchmark datasets, i.e., ImageNet-256 & 512, MS-COCO, and CC3M. Our code is available at https://github.com/LeapLabTHU/ImprovedNAT.

PaperPDFConference PDFCodeCode 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 16 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 12 ran (4 with no instrument failure; 8 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.

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

leaplabthu/improvednat officialmentioned in papermentioned on GitHubpytorchMITSyntology: 16 samples, 12 ran (8 instrument-failed) · 4 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.

Code Syntology ran Syntology

16 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 8 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
8ran · our draft was wrong
3ran
4unverified

Licence: 9 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 9 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from leaplabthu/improvednat. “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.

leaplabthu/improvednat official repository 16 samples, 12 ran (8 instrument-failed) · 4 unverified
BertEmbeddings in 21 papers libs/nat_model.py ran · metamorphic tier: invariant MIT (permissive) · 7001b82c42bcf7a8 · report fixture: signature input_ids:Tensor/2/int · returned Tensor · level recorded 2026-09-22
add_gumbel_noise in 32 papers
census: 7 implementations from 12 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
libs/nat_misc.py ran · our draft was wrong MIT (permissive) · 9ef9985f5609c318 · report fixture: signature t:Tensor/2/float, temperature:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22
center_crop in 48 papers dataset.py ran MIT (permissive) here; the stored copy is pointer only · f057bf3471d77c43 · report fixture: signature width:int/0/int, height:int/0/int, img:ndarray/3/int · returned ndarray · level recorded 2026-09-24
center_crop_arr in 79 papers dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · f8b4a29a52612a41 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int · returned ndarray · level recorded 2026-09-25
count_params in 80 papers taming/modules/util.py ran · honoured contract MIT (permissive) · 5ef87f1a172f152b · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
customized_lr_scheduler utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 4c4a870f0a791ce8 · report fixture: signature optimizer:SGD/0/?, warmup_steps:int/0/int · returned LambdaLR · level recorded 2026-09-25
get_lr_scheduler in 17 papers utils.py ran MIT (permissive) · 20380250dc418d5c · report fixture: signature optimizer:SGD/0/?, name:str/0/str, args:NoneType/0/?, warmup_steps:int/0/int · returned LambdaLR · level recorded 2026-09-24
get_optimizer in 228 papers utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 7328f4d3c151e58b · report fixture: signature params:generator/0/?, name:str/0/str · returned Adam · level recorded 2026-09-25
get_parameter_device in 18 papers taming/models/modeling_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · bfdddec04a7257ca · report fixture: signature parameter:callable/0/? · returned device · level recorded 2026-09-25
get_parameter_dtype in 20 papers taming/models/modeling_utils.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 4f52e71d06a15422 · report fixture: signature parameter:callable/0/? · returned dtype · level recorded 2026-09-25
load_state_dict in 114 papers taming/models/modeling_utils.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 934f2eb98d647821 · report fixture: signature checkpoint_file:str/0/str · returned dict · level recorded 2026-09-25
random_crop_arr in 41 papers dataset.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 05d1f95a391c0ec3 · report fixture: signature pil_image:Image/0/?, image_size:int/0/int, min_crop_frac:float/0/float, max_crop_frac:float/0/float · returned ndarray · level recorded 2026-09-24
UViT libs/nat_model.py unverified MIT (permissive) · d5608565226216c9 · report
get_logger in 383 papers taming/models/logging.py unverified MIT (permissive) here; the stored copy is pointer only · 376bf22d5737fc2a · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for AutoNAT (graph method: AutoNAT). 8 bricks; individually on a fixture: 5 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. UViT entry · level 0 · unverified · d5608565226216c9
  2. BertEmbeddings model · level 1 · ran · 7001b82c42bcf7a8
  3. Block model · level 0 · unverified · edd136332f6ae67e
  4. MlmLayer model · level 1 · ran · 72ec0347648af855
  5. trunc_normal_ helper · level 1 · ran; the contract check could not run · 02566da69866c48c
  6. Attention model · level 0 · unverified · c707cacd32c81e73
  7. Mlp helper · level 1 · ran · a1715055832f71fd
  8. _no_grad_trunc_normal_ helper · level 1 · ran; the contract check could not run · fa2dd3be10cf9804

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="2406.05478") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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