Papers › Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis

7 Sep 2023CVPR 2025 1arXiv:2309.03904archive 2025-07-28

Jiapeng Zhu, Ceyuan Yang, Kecheng Zheng, Yinghao Xu, Zifan Shi, Yujun Shen

Due to the difficulty in scaling up, generative adversarial networks (GANs) seem to be falling from grace on the task of text-conditioned image synthesis. Sparsely-activated mixture-of-experts (MoE) has recently been demonstrated as a valid solution to training large-scale models with limited computational resources. Inspired by such a philosophy, we present Aurora, a GAN-based text-to-image generator that employs a collection of experts to learn feature processing, together with a sparse router to help select the most suitable expert for each feature point. To faithfully decode the sampling stochasticity and the text condition to the final synthesis, our router adaptively makes its decision by taking into account the text-integrated global latent code. At 64x64 image resolution, our model trained on LAION2B-en and COYO-700M achieves 6.2 zero-shot FID on MS COCO. We release the code and checkpoints to facilitate the community for further development.

PaperPDFConference PDFCodeCode 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

Syntology 24 code samples harvested from 1 repository linked to this paper: 19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 24 samples from 1 repository, 19 ran (18 with no instrument failure; 1 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.

zhujiapeng/aurora officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 24 samples, 19 ran (1 instrument-failed) · 5 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

24 samples harvested: 19 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 0 honoured, 0 violated, 18 with no contract checked; 1 where Syntology's instrument failed) · 5 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.

1ran · our draft was wrong
18ran
5unverified

Licence: 24 of the 24 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 zhujiapeng/aurora. “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.

zhujiapeng/aurora official repository 24 samples, 19 ran (1 instrument-failed) · 5 unverified
all_gather in 119 papers models/utils/ops.py ran fingerprinted licence not identified · pointer only · 7c59a8472c6eaffe · report fixture: signature tensor:Tensor/2/float · returned Tensor · level recorded 2026-09-24
checkpoint in 42 papers models/text_generator.py ran licence not identified · pointer only · 92ecbfa6e2931d1f · report fixture: signature func:callable/0/?, inputs:list/1/Tensor, params:list/1/Tensor, flag:bool/0/bool · returned Tensor · level recorded 2026-09-24
format_image_size utils/formatting_utils.py ran fingerprinted licence not identified · pointer only · 028697b602cf499b · report fixture: signature size:int/0/int · returned tuple · level recorded 2026-09-24
format_range utils/formatting_utils.py ran licence not identified · pointer only · 7ca917a87c991b95 · report fixture: signature obj:tuple/1/int, min_val:int/0/int, max_val:int/0/int · returned tuple · level recorded 2026-09-24
format_time in 140 papers utils/formatting_utils.py ran fingerprinted licence not identified · pointer only · 2a7a8c6e7e8bf0e5 · report fixture: signature seconds:float/0/float · returned str · level recorded 2026-09-24
get_blank_image utils/image_utils.py ran licence not identified · pointer only · ffa47ea5654a8f02 · report fixture: signature height:int/0/int, width:int/0/int, channels:int/0/int, use_black:bool/0/bool · returned ndarray · level recorded 2026-09-24
get_cache_dir in 14 papers utils/misc.py ran licence not identified · pointer only · e6573e8618e29edb · report fixture: signature use_repo_name:bool/0/bool · returned str · level recorded 2026-09-24
get_ddp_module utils/dist_utils.py ran licence not identified · pointer only · 766e3a74f52dcc32 · report fixture: signature model:callable/0/? · returned SimpleModel · level recorded 2026-09-24
load_image in 273 papers utils/image_utils.py ran licence not identified · pointer only · 11932a80d2ccef24 · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-24
parse_bool in 9 papers utils/parsing_utils.py ran licence not identified · pointer only · 480b3d5e5171def6 · report fixture: signature arg:str/0/str · returned bool · level recorded 2026-09-24
parse_file_format utils/misc.py ran fingerprinted licence not identified · pointer only · d2c2c3208907eae9 · report fixture: signature path:str/0/str · returned str · level recorded 2026-09-24
parse_float in 6 papers utils/parsing_utils.py ran licence not identified · pointer only · 77045e5d954b160a · report fixture: signature arg:str/0/str · returned float · level recorded 2026-09-24
parse_int in 5 papers utils/parsing_utils.py ran licence not identified · pointer only · 1c53e0c56a162b36 · report fixture: signature arg:str/0/str · returned int · level recorded 2026-09-24
read_text in 29 papers run_synthesize.py ran licence not identified · pointer only · 665e2fc06573f4d0 · report fixture: signature text_path:str/0/str · returned list · level recorded 2026-09-24
router_z_loss_func models/text_generator.py ran fingerprinted licence not identified · pointer only · 08d6b8ac35009b66 · report fixture: signature router_logits:Tensor/3/float · returned Tensor · level recorded 2026-09-24
run_mapping run_interpolate.py ran licence not identified · pointer only · b7f4d2a919b82370 · report fixture: signature G:callable/0/?, z:Tensor/2/float, global_text:Tensor/2/float · returned Tensor · level recorded 2026-09-24
run_synthesize run_interpolate.py ran licence not identified · pointer only · 86151dc361b7abcd · report fixture: signature G:callable/0/?, wp:Tensor/2/float, local_text:Tensor/2/float · returned Tensor · level recorded 2026-09-24
run_text_head run_interpolate.py ran licence not identified · pointer only · 1905d8c9da15da33 · report fixture: signature G:callable/0/?, context:Tensor/2/float, eot_ind:NoneType/0/? · returned tuple · level recorded 2026-09-24
zero_module in 184 papers models/text_generator.py ran · our draft was wrong no licence file found · pointer only · 129b804760b3115f · report fixture: signature module:callable/0/? · returned SimpleModule · level recorded 2026-09-22
check_file_ext utils/misc.py unverified licence not identified · pointer only · 4a9781a78a594e12 · report
concat_all_gather in 141 papers
census: 7 implementations from 7 papers, 2 distinct outputs on one shared input
models/clip_model.py unverified licence not identified · pointer only · 66258b2be72f04a5 · report
list_pretrained_models_by_tag in 5 papers models/clip_model.py unverified licence not identified · pointer only · f56096eac6a0f2b3 · report
list_pretrained_tags_by_model in 5 papers models/clip_model.py unverified licence not identified · pointer only · 4da92d32e1ce1c72 · report
resize_image in 74 papers utils/image_utils.py unverified licence not identified · pointer only · 93a805b315b09a0b · report

Tasks

Image GenerationMixture-of-ExpertsPhilosophy

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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