Papers › No Other Representation Component Is Needed: Diffusion Transformers Can Provide...

No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves

5 May 2025arXiv:2505.02831archive 2025-07-28

Dengyang Jiang, Mengmeng Wang, Liuzhuozheng Li, Lei Zhang, Haoyu Wang, Wei Wei, Guang Dai, Yanning Zhang, Jingdong Wang

Recent studies have demonstrated that learning a meaningful internal representation can both accelerate generative training and enhance the generation quality of diffusion transformers. However, existing approaches necessitate to either introduce an external and complex representation training framework or rely on a large-scale, pre-trained representation foundation model to provide representation guidance during the original generative training process. In this study, we posit that the unique discriminative process inherent to diffusion transformers enables them to offer such guidance without requiring external representation components. We therefore propose Self-Representation Alignment (SRA), a simple yet straightforward method that obtains representation guidance through a self-distillation manner. Specifically, SRA aligns the output latent representation of the diffusion transformer in the earlier layer with higher noise to that in the later layer with lower noise to progressively enhance the overall representation learning during only the generative training process. Experimental results indicate that applying SRA to DiTs and SiTs yields consistent performance improvements. Moreover, SRA not only significantly outperforms approaches relying on auxiliary, complex representation training frameworks but also achieves performance comparable to methods that are heavily dependent on powerful external representation priors.

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="2505.02831")

Code

Syntology Ran 7 of 8 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 1 ran · honoured contract; 4 ran · our draft was wrong; 2 ran with no contract checked.

By repository: official repository: 8 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

vvvvvjdy/sra officialmentioned in papermentioned on GitHubpytorch 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; 7 ran; 1 honoured the contract we drafted; 1 has 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
4ran · our draft was wrong
2ran
1unverified

Licence: 0 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 vvvvvjdy/sra. “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.

SRALoss vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 60a542850beb08a6 · report
Simpleloss vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · metamorphic tier: invariant MIT (permissive) · 5d15aa12e72b1ecf · report
_build_group_ids_from_counts vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · our draft was wrong MIT (permissive) · 86f835082a2f2ee5 · report
_compute_group_counts vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · our draft was wrong MIT (permissive) · 3fe10dc914e6000c · report
_mix_group_scalars vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · our draft was wrong MIT (permissive) · 46649503b5c7e270 · report
_normalize_mask_ratios vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · honoured contract fingerprinted MIT (permissive) · a49bb03f59ee436f · report
mean_flat vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 9b73352352dc3d0e · report
_expand_group_scalars vvvvvjdy/sra/SiT-SRA_DTS_AS/loss.py official repository unverified MIT (permissive) · 39b170fc9ad7e362 · report

Tasks

Image GenerationRepresentation Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 SiT-XL + SRA FID 1.58 #28 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