Papers › Taming Scalable Visual Tokenizer for Autoregressive Image Generation

Taming Scalable Visual Tokenizer for Autoregressive Image Generation

3 Dec 2024arXiv:2412.02692archive 2025-07-28

Fengyuan Shi, Zhuoyan Luo, Yixiao Ge, Yujiu Yang, Ying Shan, LiMin Wang

Existing vector quantization (VQ) methods struggle with scalability, largely attributed to the instability of the codebook that undergoes partial updates during training. The codebook is prone to collapse as utilization decreases, due to the progressively widening distribution gap between non-activated codes and visual features. To solve the problem, we propose Index Backpropagation Quantization (IBQ), a new VQ method for the joint optimization of all codebook embeddings and the visual encoder. Applying a straight-through estimator on the one-hot categorical distribution between the encoded feature and codebook, all codes are differentiable and maintain a consistent latent space with the visual encoder. IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook (2¹⁸) with high dimension (256) and high utilization. Experiments on the standard ImageNet benchmark demonstrate the scalability and superiority of IBQ, achieving competitive results on both reconstruction (1.00 rFID) and autoregressive visual generation (2.05 gFID). The code and models are available at https://github.com/TencentARC/SEED-Voken.

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 (tencentarc/seed-voken) is linked to this paper; the 10 samples below come from 1 community repository, and 3 more are identical to code Syntology harvested from another paper's repository. Syntology harvested code from tencentarc/seed-voken for another paper.

tencentarc/seed-voken: Syntology's graph links these samples to Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation (arXiv:2409.04410; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 13 code samples: 10 from 1 repository linked to this paper, 3 identical to code harvested from another paper's repository. Across all 13: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 10 samples from 1 repository, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed); 3 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 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. 2 of the 13 samples that ran have no recorded date.

tencentarc/seed-voken officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation (arXiv:2409.04410; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
tencentarc/open-magvit2 mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 10 ran (4 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

13 samples harvested: 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 0 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
1ran · violated contract
6ran · our draft was wrong
5ran

Licence: 7 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. For 4 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 tencentarc/open-magvit2. 3 samples are 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”. “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.

tencentarc/open-magvit2 community (archive-listed) 10 samples, 10 ran (4 instrument-failed) · 0 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/Open_MAGVIT2/modules/diffusionmodules/improved_model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
depth_to_space in 7 papers src/Open_MAGVIT2/modules/diffusionmodules/improved_model.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 3743889a7a1ed998 · report fixture: signature x:Tensor/4/float, block_size:int/0/int · returned Tensor · level recorded 2026-09-22
depth_to_space3d src/Open_MAGVIT2/modules/diffusionmodules/improved_video_model.py ran Apache-2.0 (permissive) · 523ecb8d3aa7e677 · report fixture: signature x:Tensor/5/float, block_size:list/1/int · returned Tensor · level recorded 2026-09-24
disabled_train in 172 papers src/Open_MAGVIT2/models/cond_transformer.py ran · violated contract Apache-2.0 (permissive) · 4cb732f513d69dfd · report fixture: signature self:callable/0/?, mode:bool/0/bool · returned SimpleModel · level recorded, date not recorded
flatten_t_dim src/Open_MAGVIT2/modules/util.py ran fingerprinted Apache-2.0 (permissive) · c16bc40c0efe0d76 · report fixture: signature x:Tensor/5/float · returned Tensor · level recorded 2026-09-24
get_ckpt_path in 30 papers src/Open_MAGVIT2/util.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · e70eb36cf08faee4 · report fixture: signature name:str/0/str, root:str/0/str, check:bool/0/bool · returned str · level recorded 2026-09-24
md5_hash in 33 papers src/Open_MAGVIT2/util.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 07d90bd6ae1be7db · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-22
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
src/Open_MAGVIT2/modules/util.py ran Apache-2.0 (permissive) · f772835c441ad58e · report fixture: signature videos:Tensor/5/float, target_resolution:tuple/1/int · returned Tensor · level recorded 2026-09-24
retrieve in 15 papers src/Open_MAGVIT2/util.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 31543f3e2c18272e · report fixture: signature list_or_dict:dict/0/?, key:str/0/str, splitval:str/0/str, default:NoneType/0/?, expand:bool/0/bool, pass_success:bool/0/bool · returned int · level recorded 2026-09-24
unflatten_t_dim src/Open_MAGVIT2/modules/util.py ran fingerprinted Apache-2.0 (permissive) · 4def1646226b2fac · report fixture: signature x:Tensor/4/float, t:int/0/int · returned Tensor · level recorded 2026-09-24
Repository not located 3 samples, 3 ran (2 instrument-failed) · 0 unverified
3 samples are 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.
adopt_weight in 12 papers repository not located ran · honoured contract fingerprinted licence of this copy not recorded · 7439a9d4c6be04b0 · report fixture: signature weight:float/0/float, global_step:int/0/int, threshold:int/0/int, value:float/0/float · returned float · level recorded 2026-09-22
hinge_d_loss in 19 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 22a83df891d750c6 · report fixture: signature logits_real:Tensor/2/float, logits_fake:Tensor/2/float · returned Tensor · level recorded 2026-09-22
vanilla_d_loss in 16 papers repository not located ran · our draft was wrong fingerprinted licence of this copy not recorded · 263c54290c553ddd · report fixture: signature logits_real:Tensor/1/float, logits_fake:Tensor/1/float · returned Tensor · level recorded 2026-09-22

Tasks

Image GenerationImage ReconstructionQuantization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Reconstruction ImageNet IBQ (16x16) FID 1.00 #6 of 15 Archive leaderboard report
Image Reconstruction ImageNet IBQ (16x16) LPIPS 0.2030 #6 of 15 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.

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