Papers › Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

Diffusion Bridge AutoEncoders for Unsupervised Representation Learning

27 May 2024arXiv:2405.17111archive 2025-07-28

Yeongmin Kim, Kwanghyeon Lee, Minsang Park, Byeonghu Na, Il-Chul Moon

Diffusion-based representation learning has achieved substantial attention due to its promising capabilities in latent representation and sample generation. Recent studies have employed an auxiliary encoder to identify a corresponding representation from a sample and to adjust the dimensionality of a latent variable z. Meanwhile, this auxiliary structure invokes information split problem because the diffusion and the auxiliary encoder would divide the information from the sample into two representations for each model. Particularly, the information modeled by the diffusion becomes over-regularized because of the static prior distribution on xT. To address this problem, we introduce Diffusion Bridge AuteEncoders (DBAE), which enable z-dependent endpoint xT inference through a feed-forward architecture. This structure creates an information bottleneck at z, so xT becomes dependent on z in its generation. This results in two consequences: 1) z holds the full information of samples, and 2) xT becomes a learnable distribution, not static any further. We propose an objective function for DBAE to enable both reconstruction and generative modeling, with their theoretical justification. Empirical evidence supports the effectiveness of the intended design in DBAE, which notably enhances downstream inference quality, reconstruction, and disentanglement. Additionally, DBAE generates high-fidelity samples in the unconditional generation.

PaperPDFCode 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 27 code samples harvested from 3 repositories linked to this paper: 19 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 10 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: found in paper text by Syntology: 27 samples from 3 repositories, 19 ran (7 with no instrument failure; 12 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 3 of the 19 samples that ran have no recorded date.

openai/guided-diffusion found in paper text by SyntologyMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Label-Efficient Hyperspectral Image Classification via Spectral FiLM Modulation of... (arXiv:2512.03430; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 12 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
ckczzj/PDAE found in paper text by SyntologySyntology: 12 samples, 6 ran (4 instrument-failed) · 6 unverified report
yue-zhongqi/diti found in paper text by SyntologySyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
aailab-kaist/DBAE found in paper text by SyntologyApache-2.0Syntology: 13 samples, 12 ran (8 instrument-failed) · 1 unverified report
ericyeats/nashae-beamsynthesis found in paper text by SyntologySyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NashAE: Disentangling Representations through Adversarial Covariance Minimization (arXiv:2209.10677; that paper's own run record: 7 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
GaParmar/clean-fid found in paper text by SyntologySyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to On Aliased Resizing and Surprising Subtleties in GAN Evaluation (arXiv:2104.11222; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

27 samples harvested: 19 ran (of which 3 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 0 violated, 4 with no contract checked; 12 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
10ran · our draft was wrong
2ran; the contract check could not run
4ran
8unverified

Licence: 19 of the 27 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 3 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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.

ckczzj/PDAE found in paper text by Syntology 12 samples, 6 ran (4 instrument-failed) · 6 unverified
DDIM in 5 papers trainer/train_representation_learning.py ran no licence file found · pointer only · f7487b6d19383fd2 · report fixture: returned DDIM · level recorded 2026-09-22
apply_to_sample in 5 papers trainer/train_representation_learning.py ran · our draft was wrong no licence file found · pointer only · e6a9932fddabc671 · report fixture: signature f:callable/0/?, sample:dict/0/? · returned dict · level recorded 2026-09-22
load_yaml in 107 papers trainer/train_representation_learning.py ran · our draft was wrong no licence file found · pointer only · 23a955cb5ab536ed · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
move_to_cuda in 22 papers trainer/train_representation_learning.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 5999a3c31acadfe9 · report fixture: returned dict · level recorded 2026-09-22
save_image in 18 papers trainer/train_representation_learning.py ran · our draft was wrong no licence file found · pointer only · acd70fe09760a8b6 · report fixture: signature images:ndarray/4/int, save_path:str/0/str, captions:list/1/str, gts:ndarray/4/int, masked_gts:ndarray/4/int, num_cols:int/0/int · returned Figure · level recorded 2026-09-22
set_worker_seed_builder trainer/train_representation_learning.py ran no licence file found · pointer only · 9b1ad82621dea0cf · report fixture: returned set_worker_seed_builder · level recorded 2026-09-22
BaseTrainer in 16 papers trainer/train_representation_learning.py unverified no licence file found · pointer only · 59d0f7c7bd4e6720 · report
GaussianDiffusion in 61 papers trainer/train_representation_learning.py unverified no licence file found · pointer only · c7bd746e2c86ba6c · report
RepresentationLearningTrainer trainer/train_representation_learning.py unverified no licence file found · pointer only · 690c2ec6cac49099 · report
init_distributed_mode in 5 papers trainer/train_representation_learning.py unverified no licence file found · pointer only · 05a2d13828b0fcb0 · report
save_yaml trainer/train_representation_learning.py unverified no licence file found · pointer only · 7f266a03bbbc3136 · report
set_seed in 49 papers trainer/train_representation_learning.py unverified no licence file found · pointer only · 0081e6dcf509161e · report
yue-zhongqi/diti found in paper text by Syntology 2 samples, 1 ran (0 instrument-failed) · 1 unverified
DDIM in 5 papers model/diffusion/gaussian_diffusion.py ran no licence file found · pointer only · 94462cd3ef4ce032 · report fixture: returned DDIM · level recorded 2026-09-22
GaussianDiffusion in 61 papers model/diffusion/gaussian_diffusion.py unverified no licence file found · pointer only · b9372fbb285f6852 · report
aailab-kaist/DBAE found in paper text by Syntology 13 samples, 12 ran (8 instrument-failed) · 1 unverified
UpBlock in 15 papers ddbm/unet.py ran · our draft was wrong Apache-2.0 (permissive) · 5a2cb2800ec7d0de · report fixture: signature in_planes:int/0/int, out_planes:int/0/int · returned Sequential · level recorded 2026-09-24
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
ddbm/losses.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cfd76fd0d89574a4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
create_window in 82 papers eval_reconstruction.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 6154e3744ece5728 · report fixture: signature window_size:int/0/int, channel:int/0/int · returned Tensor · level recorded 2026-09-22
discretized_gaussian_log_likelihood in 124 papers
census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
ddbm/losses.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · cd33283d615fb3d7 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded
gaussian in 218 papers
census: 8 implementations from 9 papers, 8 distinct outputs across 4 buckets, one shared input per bucket
eval_reconstruction.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c56b7ef16f309a45 · report fixture: signature window_size:int/0/int, sigma:float/0/float · returned Tensor · level recorded, date not recorded
get_workdir dbae_infer_class.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 874a2882475bf3de · report fixture: signature exp:str/0/str · returned str · level recorded 2026-09-22
load_databatch datasets/imagenet.py ran Apache-2.0 (permissive) · e2f262ec3f30d30c · report fixture: signature data_folder:str/0/str, img_size:int/0/int, filename:str/0/str · returned tuple · level recorded 2026-09-24
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
ddbm/losses.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · cf2798b666b231ca · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
soft_clamp5 in 6 papers ddbm/unet.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 1b3468f8f7313851 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
ssim in 112 papers eval_reconstruction.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 9151c793f90473f0 · report fixture: signature img1:Tensor/4/float, img2:Tensor/4/float, window_size:int/0/int, size_average:bool/0/bool · returned Tensor · level recorded 2026-09-26
unpickle in 45 papers datasets/imagenet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 4ebc0e09cb353eac · report fixture: signature file:str/0/str · returned dict · level recorded 2026-09-25
weight_init in 73 papers ddbm/edm_unet.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · d41a4250066bce93 · report fixture: signature shape:tuple/1/int, mode:str/0/str, fan_in:int/0/int, fan_out:int/0/int · returned Tensor · level recorded 2026-09-22
get_t datasets/imagenet.py unverified Apache-2.0 (permissive) · d9fa2e8aae38ad38 · 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. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

2 sibling assemblies for Diffusion Bridge AutoEncoders (DBAE) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Diffusion Bridge AutoEncoders (DBAE) (graph method: Diffusion Bridge AutoEncoders (DBAE)). 2 bricks; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. GaussianDiffusion entry · level 0 · unverified · b9372fbb285f6852
  2. DDIM helper · level 1 · ran · 94462cd3ef4ce032

harvested Assembly for Diffusion Bridge AutoEncoders (DBAE) (graph method: Diffusion Bridge AutoEncoders (DBAE)). 12 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. RepresentationLearningTrainer entry · level 0 · unverified · 690c2ec6cac49099
  2. BaseTrainer helper · level 0 · unverified · 59d0f7c7bd4e6720
  3. GaussianDiffusion model · level 0 · unverified · c7bd746e2c86ba6c
  4. load_yaml helper · level 1 · ran · our draft was wrong · 23a955cb5ab536ed
  5. move_to_cuda helper · level 1 · ran; the contract check could not run (RAISES) · 5999a3c31acadfe9
  6. save_image helper · level 1 · ran · our draft was wrong · acd70fe09760a8b6
  7. init_distributed_mode helper · level 0 · unverified · 05a2d13828b0fcb0
  8. save_yaml helper · level 0 · unverified · 7f266a03bbbc3136
  9. set_seed helper · level 0 · unverified · 0081e6dcf509161e
  10. set_worker_seed_builder helper · level 1 · ran · 9b1ad82621dea0cf
  11. DDIM helper · level 1 · ran · f7487b6d19383fd2
  12. apply_to_sample helper · level 1 · ran · our draft was wrong · e6a9932fddabc671

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="2405.17111") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DisentanglementRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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