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 Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2412.02692")

Code

Syntology Ran 9 of 13 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 5 ran · our draft was wrong; 2 ran with no contract checked.

By repository: community (archive-listed): 10 samples from 1 repository, 6 ran; 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.

tencentarc/seed-voken officialmentioned in papermentioned on GitHubpytorch report
tencentarc/open-magvit2 mentioned on GitHubpytorchApache-2.0 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

13 samples harvested; 9 ran; 1 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
2ran
4unverified

Licence: 3 of the 13 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 tencentarc/open-magvit2. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

swish tencentarc/open-magvit2/src/Open_MAGVIT2/modules/diffusionmodules/improved_model.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 0f786c407fb1ee4c · report
depth_to_space tencentarc/open-magvit2/src/Open_MAGVIT2/modules/diffusionmodules/improved_model.py community (archive-listed) ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 3743889a7a1ed998 · report
disabled_train tencentarc/open-magvit2/src/Open_MAGVIT2/models/cond_transformer.py community (archive-listed) ran · violated contract Apache-2.0 (permissive) · 4cb732f513d69dfd · report
get_ckpt_path tencentarc/open-magvit2/src/Open_MAGVIT2/util.py community (archive-listed) ran Apache-2.0 (permissive) · e70eb36cf08faee4 · report
md5_hash tencentarc/open-magvit2/src/Open_MAGVIT2/util.py community (archive-listed) ran · our draft was wrong Apache-2.0 (permissive) · 07d90bd6ae1be7db · report
retrieve tencentarc/open-magvit2/src/Open_MAGVIT2/util.py community (archive-listed) ran Apache-2.0 (permissive) · 31543f3e2c18272e · report
depth_to_space3d tencentarc/open-magvit2/src/Open_MAGVIT2/modules/diffusionmodules/improved_video_model.py community (archive-listed) unverified Apache-2.0 (permissive) · 523ecb8d3aa7e677 · report
flatten_t_dim tencentarc/open-magvit2/src/Open_MAGVIT2/modules/util.py community (archive-listed) unverified Apache-2.0 (permissive) · c16bc40c0efe0d76 · report
preprocess tencentarc/open-magvit2/src/Open_MAGVIT2/modules/util.py community (archive-listed) unverified Apache-2.0 (permissive) · f772835c441ad58e · report
unflatten_t_dim tencentarc/open-magvit2/src/Open_MAGVIT2/modules/util.py community (archive-listed) unverified Apache-2.0 (permissive) · 4def1646226b2fac · report
adopt_weight identical code first harvested elsewhere ran · honoured contract fingerprinted licence of this copy not recorded · 7439a9d4c6be04b0 · report
hinge_d_loss identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 22a83df891d750c6 · report
vanilla_d_loss identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 263c54290c553ddd · report

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