Papers › "Principal Components" Enable A New Language of Images

"Principal Components" Enable A New Language of Images

11 Mar 2025arXiv:2503.08685archive 2025-07-28

Xin Wen, Bingchen Zhao, Ismail Elezi, Jiankang Deng, Xiaojuan Qi

We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space. While existing visual tokenizers primarily optimize for reconstruction fidelity, they often neglect the structural properties of the latent space -- a critical factor for both interpretability and downstream tasks. Our method generates a 1D causal token sequence for images, where each successive token contributes non-overlapping information with mathematically guaranteed decreasing explained variance, analogous to principal component analysis. This structural constraint ensures the tokenizer extracts the most salient visual features first, with each subsequent token adding diminishing yet complementary information. Additionally, we identified and resolved a semantic-spectrum coupling effect that causes the unwanted entanglement of high-level semantic content and low-level spectral details in the tokens by leveraging a diffusion decoder. Experiments demonstrate that our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system. Moreover, auto-regressive models trained on our token sequences achieve performance comparable to current state-of-the-art methods while requiring fewer tokens for training and inference.

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="2503.08685")

Code

Syntology Ran 5 of 17 code samples harvested from 1 repository linked to this paper; 12 have no recorded run. Of those that ran: 3 ran · honoured contract; 2 ran · our draft was wrong.

By repository: official repository: 17 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

visual-gen/semanticist officialmentioned on GitHubpytorchMIT 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

17 samples harvested; 5 ran; 3 honoured the contract we drafted; 12 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.

3ran · honoured contract
2ran · our draft was wrong
12unverified

Licence: 0 of the 17 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 visual-gen/semanticist. “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.

build_mlp visual-gen/semanticist/semanticist/stage1/diffuse_slot.py official repository ran · our draft was wrong MIT (permissive) · b05a447cc3b9e991 · report
find_multiple visual-gen/semanticist/semanticist/stage2/gpt.py official repository ran · honoured contract fingerprinted MIT (permissive) · f6ff7671338c9c92 · report
get_2d_sincos_pos_embed visual-gen/semanticist/semanticist/stage1/diffusion_transfomer.py official repository ran · honoured contract MIT (permissive) · c92c27c924b517e8 · report
modulate visual-gen/semanticist/semanticist/stage1/diffusion_transfomer.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 03310bba324ae4fb · report
modulate visual-gen/semanticist/semanticist/stage2/diffloss.py official repository ran · honoured contract fingerprinted MIT (permissive) · 62fcb3912a967a50 · report
concat_all_gather visual-gen/semanticist/semanticist/engine/trainer_utils.py official repository unverified MIT (permissive) · d0aca56def6a1f55 · report
decode_n_tokens visual-gen/semanticist/semanticist/stage2/generate.py official repository unverified MIT (permissive) · c10d644e68f17884 · report
decode_one_token visual-gen/semanticist/semanticist/stage2/generate.py official repository unverified MIT (permissive) · f6e7c115a93e25a8 · report
drop_path visual-gen/semanticist/semanticist/stage1/vision_transformer.py official repository unverified MIT (permissive) · 4134f673786a2abe · report
get_1d_sincos_pos_embed visual-gen/semanticist/semanticist/stage1/pos_embed.py official repository unverified MIT (permissive) · e13eb3c1606755e6 · report
get_2d_sincos_pos_embed visual-gen/semanticist/semanticist/stage1/pos_embed.py official repository unverified MIT (permissive) · 9417ae492629cf06 · report
get_2d_sincos_pos_embed_from_grid visual-gen/semanticist/semanticist/stage1/diffusion_transfomer.py official repository unverified MIT (permissive) · 665d8a4e8f673a4c · report
get_2d_sincos_pos_embed_from_grid visual-gen/semanticist/semanticist/stage1/pos_embed.py official repository unverified MIT (permissive) · 4fd80de79832745d · report
get_obj_from_str visual-gen/semanticist/semanticist/engine/trainer_utils.py official repository unverified MIT (permissive) · 1be6845a690a8075 · report
instantiate_from_config visual-gen/semanticist/semanticist/engine/trainer_utils.py official repository unverified MIT (permissive) · e6197485fe096b58 · report
interpolate_features visual-gen/semanticist/semanticist/stage1/diffuse_slot.py official repository unverified MIT (permissive) · 1f5b50d685e20502 · report
prefill visual-gen/semanticist/semanticist/stage2/generate.py official repository unverified MIT (permissive) · d90c14200bec99a5 · report

Tasks

Decoder

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNDiffusion

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