Papers › Return of Unconditional Generation: A Self-supervised Representation Generation Method

Return of Unconditional Generation: A Self-supervised Representation Generation Method

6 Dec 2023arXiv:2312.03701archive 2025-07-28

Tianhong Li, Dina Katabi, Kaiming He

Unconditional generation -- the problem of modeling data distribution without relying on human-annotated labels -- is a long-standing and fundamental challenge in generative models, creating a potential of learning from large-scale unlabeled data. In the literature, the generation quality of an unconditional method has been much worse than that of its conditional counterpart. This gap can be attributed to the lack of semantic information provided by labels. In this work, we show that one can close this gap by generating semantic representations in the representation space produced by a self-supervised encoder. These representations can be used to condition the image generator. This framework, called Representation-Conditioned Generation (RCG), provides an effective solution to the unconditional generation problem without using labels. Through comprehensive experiments, we observe that RCG significantly improves unconditional generation quality: e.g., it achieves a new state-of-the-art FID of 2.15 on ImageNet 256x256, largely reducing the previous best of 5.91 by a relative 64%. Our unconditional results are situated in the same tier as the leading class-conditional ones. We hope these encouraging observations will attract the community's attention to the fundamental problem of unconditional generation. Code is available at https://github.com/LTH14/rcg.

PaperPDFCodeCode 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 18 code samples harvested from 1 repository linked to this paper: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 12 ran (9 with no instrument failure; 3 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.

LTH14/rcg officialmentioned in papermentioned on GitHubpytorchSyntology: 18 samples, 12 ran (3 instrument-failed) · 6 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

18 samples harvested: 12 ran (of which 7 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 6 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.

3ran · our draft was wrong
9ran
6unverified

Licence: 0 of the 18 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 LTH14/rcg. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

LTH14/rcg official repository 18 samples, 12 ran (3 instrument-failed) · 6 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
pixel_generator/mage/models_mage.py ran MIT (permissive) · 33aedbcfd18d75e0 · report fixture: signature x:Tensor/3/float · returned tuple · level recorded 2026-09-24
BertEmbeddings in 21 papers pixel_generator/mage/models_mage.py ran MIT (permissive) · 63c52efe80c94cb3 · report fixture: returned BertEmbeddings · level recorded 2026-09-22
Block in 252 papers
census: 5 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
pixel_generator/mage/models_mage.py ran MIT (permissive) · 607e78af8a011f8d · report fixture: returned Block · level recorded 2026-09-22
DDIMSampler in 6 papers pixel_generator/mage/models_mage.py ran MIT (permissive) · 950818a420758dbe · report fixture: returned DDIMSampler · level recorded 2026-09-22
Decoder in 210 papers pixel_generator/mage/models_mage.py ran fingerprinted MIT (permissive) · 9c54ac910ba566df · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers pixel_generator/mage/models_mage.py ran MIT (permissive) · 2deab9d7e8ce0dcd · report fixture: returned Encoder · level recorded 2026-09-22
MlmLayer pixel_generator/mage/models_mage.py ran MIT (permissive) · 72ec0347648af855 · report fixture: returned MlmLayer · level recorded 2026-09-22
ResnetBlock in 49 papers pixel_generator/mage/models_mage.py ran MIT (permissive) · 30fa834a4a883839 · report fixture: signature x:Tensor/4/float, temb:Tensor/2/float · returned Tensor · level recorded 2026-09-24
VectorQuantizer in 26 papers pixel_generator/mage/models_mage.py ran fingerprinted MIT (permissive) · 9d2f5c397afb9f4b · report fixture: returned VectorQuantizer · level recorded 2026-09-22
load_pretrained_deit pixel_generator/mage/models_mage.py ran · our draft was wrong MIT (permissive) · 43b98b8b55d12a3d · report fixture: signature model:callable/0/?, ckpt_path:str/0/str · returned MinimalModel · level recorded 2026-09-22
load_pretrained_ibot pixel_generator/mage/models_mage.py ran · our draft was wrong MIT (permissive) · c6c33009466a11bc · report fixture: signature model:callable/0/?, ckpt_path:str/0/str · returned SimpleModel · level recorded 2026-09-22
load_pretrained_moco pixel_generator/mage/models_mage.py ran · our draft was wrong MIT (permissive) · 606b6d93861e426d · report fixture: signature model:callable/0/?, ckpt_path:str/0/str · returned MinimalModel · level recorded 2026-09-22
MaskedGenerativeEncoderViT pixel_generator/mage/models_mage.py unverified MIT (permissive) · 928ed9eea191af30 · report
VQModel pixel_generator/mage/models_mage.py unverified MIT (permissive) · 5ff5b3c39cac8e4d · report
load_model in 479 papers pixel_generator/mage/models_mage.py unverified MIT (permissive) · 43c459d4c7f134b2 · report
load_model_from_config in 9 papers pixel_generator/mage/models_mage.py unverified MIT (permissive) · bf19fad78c0d01dd · report
load_pretrained_dino pixel_generator/mage/models_mage.py unverified MIT (permissive) · 751c98281389ad11 · report
mask_by_random_topk in 5 papers pixel_generator/mage/models_mage.py unverified MIT (permissive) · 92679b16417e54ec · 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 Representation-Conditioned Generation (RCG) (graph method: Representation-Conditioned Generation (RCG)). 33 bricks; individually on a fixture: 24 ran (of which 11 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 9 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

  1. MaskedGenerativeEncoderViT entry · level 0 · unverified · 928ed9eea191af30
  2. BertEmbeddings model · level 1 · ran · 63c52efe80c94cb3
  3. Block model · level 1 · ran · 607e78af8a011f8d
  4. DDIMSampler helper · level 1 · ran · 950818a420758dbe
  5. LabelSmoothingCrossEntropy loss · level 1 · ran · 60f4e5c9241d5bc8
  6. MlmLayer model · level 1 · ran · 72ec0347648af855
  7. VQModel helper · level 0 · unverified · 5ff5b3c39cac8e4d
  8. get_2d_sincos_pos_embed helper · level 1 · ran · honoured contract · 5a37690a13a6157d
  9. load_model helper · level 0 · unverified · 43c459d4c7f134b2
  10. load_pretrained_deit helper · level 1 · ran · our draft was wrong · 43b98b8b55d12a3d
  11. load_pretrained_dino helper · level 0 · unverified · 751c98281389ad11
  12. load_pretrained_ibot helper · level 1 · ran · our draft was wrong · c6c33009466a11bc
  13. load_pretrained_moco helper · level 1 · ran · our draft was wrong · 606b6d93861e426d
  14. mask_by_random_topk helper · level 0 · unverified · 92679b16417e54ec
  15. Attention model · level 1 · ran · 33aedbcfd18d75e0
  16. make_ddim_sampling_parameters helper · level 1 · ran; the contract check could not run · 3ee640131c9d4362
  17. make_ddim_timesteps helper · level 1 · ran · honoured contract · 0ea4e960ea54514c
  18. noise_like helper · level 1 · ran; the contract check could not run · 2d7200ac60d9a4bd
  19. Decoder helper · level 1 · ran · 9c54ac910ba566df
  20. Encoder helper · level 1 · ran · 2deab9d7e8ce0dcd
  21. VectorQuantizer helper · level 1 · ran · 9d2f5c397afb9f4b
  22. get_2d_sincos_pos_embed_from_grid helper · level 0 · unverified · 2884deadbb637c3e
  23. load_model_from_config helper · level 0 · unverified · bf19fad78c0d01dd
  24. checkpoint helper · level 0 · unverified · 6fe195fcfd10e259
  25. Normalize helper · level 1 · ran · our draft was wrong · c3a6b977022957cb
  26. ResnetBlock helper · level 1 · ran · 30fa834a4a883839
  27. Upsample helper · level 1 · ran · 726c85e75dfdfeb8
  28. nonlinearity helper · level 1 · ran · our draft was wrong · 3137073275f8c21a
  29. Downsample helper · level 1 · ran · f86ae8958e076367
  30. get_1d_sincos_pos_embed_from_grid helper · level 1 · ran; the contract check could not run · 5c8ea92d43ead77d
  31. instantiate_from_config helper · level 0 · unverified · ef52d142b2c30ac2
  32. CheckpointFunction helper · level 1 · ran · 69360f5b0cc8f069
  33. get_obj_from_str helper · level 1 · ran · our draft was wrong · 221b2d116fdf1032

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="2312.03701") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Conditional Image GenerationImage GenerationUnconditional Image Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 RCG-L (w/o guidance) FID 3.49 #71 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