Papers › AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model

5 Jun 2025arXiv 2025 6arXiv:2506.05289archive 2025-07-28

Pingyu Wu, Kai Zhu, Yu Liu, Longxiang Tang, Jian Yang, Yansong Peng, Wei Zhai, Yang Cao, Zheng-Jun Zha

Autoregressive image generation aims to predict the next token based on previous ones. However, existing image tokenizers encode tokens with bidirectional dependencies during the compression process, which hinders the effective modeling by autoregressive models. In this paper, we propose a novel Aligned Tokenizer (AliTok), which utilizes a causal decoder to establish unidirectional dependencies among encoded tokens, thereby aligning the token modeling approach between the tokenizer and autoregressive model. Furthermore, by incorporating prefix tokens and employing two-stage tokenizer training to enhance reconstruction consistency, AliTok achieves great reconstruction performance while being generation-friendly. On ImageNet-256 benchmark, using a standard decoder-only autoregressive model as the generator with only 177M parameters, AliTok achieves a gFID score of 1.50 and an IS of 305.9. When the parameter count is increased to 662M, AliTok achieves a gFID score of 1.35, surpassing the state-of-the-art diffusion method with 10x faster sampling speed. The code and weights are available at https://github.com/ali-vilab/alitok.

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

By repository: official repository: 8 samples from 1 repository, 4 ran (3 with no instrument failure; 1 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ali-vilab/alitok officialmentioned in papermentioned on GitHubpytorchSyntology: 8 samples, 4 ran (1 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

8 samples harvested: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 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.

1ran · our draft was wrong
3ran
4unverified

Licence: 8 of the 8 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 ali-vilab/alitok. “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.

ali-vilab/alitok official repository 8 samples, 4 ran (1 instrument-failed) · 4 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
modeling/alitok.py ran no licence file found · pointer only · 90986cade2362a6c · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/?, is_causal:bool/0/bool · returned Tensor · level recorded 2026-09-24
ResidualAttentionBlock in 38 papers modeling/alitok.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 71a046a9abe78001 · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/?, is_causal:bool/0/bool · returned Tensor · level recorded 2026-09-22
VectorQuantizer in 26 papers modeling/alitok.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8c5d87429839addc · report fixture: signature z:Tensor/4/float · returned tuple · level recorded 2026-09-22
create_npz_from_sample_folder in 30 papers sample_imagenet.py ran · our draft was wrong no licence file found · pointer only · 19a5b88fdb546606 · report fixture: signature sample_dir:str/0/str, num:int/0/int · returned str · level recorded 2026-09-22
AliTok modeling/alitok.py unverified no licence file found · pointer only · 9f49ed271158263c · report
Decoder in 210 papers modeling/alitok.py unverified no licence file found · pointer only · 71c21cc5683de18f · report
Encoder in 278 papers modeling/alitok.py unverified no licence file found · pointer only · c5d3142e52feb9a8 · report
VAutoencoder modeling/alitok.py unverified no licence file found · pointer only · ed9a3eb24c70f0c6 · 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 AliTok (graph method: AliTok). 8 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. AliTok entry · level 0 · unverified · 9f49ed271158263c
  2. VAutoencoder model · level 0 · unverified · ed9a3eb24c70f0c6
  3. Decoder model · level 0 · unverified · 71c21cc5683de18f
  4. Encoder model · level 0 · unverified · c5d3142e52feb9a8
  5. VectorQuantizer model · level 1 · ran · 8c5d87429839addc
  6. ResidualAttentionBlock helper · level 1 · ran · 71a046a9abe78001
  7. _expand_token helper · level 1 · ran · our draft was wrong · 8a18fd0e92a888ed
  8. Attention helper · level 1 · ran · 90986cade2362a6c

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="2506.05289") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 AliTok-XL, autoregressive, 662M FID 1.35 #13 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 AliTok-XL, autoregressive, 662M Inception score 318.8 #13 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 AliTok-XL, autoregressive, 318M FID 1.42 #17 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 AliTok-XL, autoregressive, 318M Inception score 326.6 #17 of 94 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

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