Papers › AdjointDEIS: Efficient Gradients for Diffusion Models

AdjointDEIS: Efficient Gradients for Diffusion Models

23 May 2024arXiv:2405.15020archive 2025-07-28

Zander W. Blasingame, Chen Liu

The optimization of the latents and parameters of diffusion models with respect to some differentiable metric defined on the output of the model is a challenging and complex problem. The sampling for diffusion models is done by solving either the probability flow ODE or diffusion SDE wherein a neural network approximates the score function allowing a numerical ODE/SDE solver to be used. However, naive backpropagation techniques are memory intensive, requiring the storage of all intermediate states, and face additional complexity in handling the injected noise from the diffusion term of the diffusion SDE. We propose a novel family of bespoke ODE solvers to the continuous adjoint equations for diffusion models, which we call AdjointDEIS. We exploit the unique construction of diffusion SDEs to further simplify the formulation of the continuous adjoint equations using exponential integrators. Moreover, we provide convergence order guarantees for our bespoke solvers. Significantly, we show that continuous adjoint equations for diffusion SDEs actually simplify to a simple ODE. Lastly, we demonstrate the effectiveness of AdjointDEIS for guided generation with an adversarial attack in the form of the face morphing problem. Our code will be released at https: //github.com/zblasingame/AdjointDEIS.

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="2405.15020")

Code

Syntology Ran 20 of 23 code samples harvested from 2 repositories linked to this paper; 3 have no recorded run. Of those that ran: 3 ran · honoured contract; 3 ran · our draft was wrong; 14 ran with no contract checked.

By repository: found in paper text by Syntology: 23 samples from 2 repositories, 20 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

zblasingame/adjointdeis officialmentioned in papermentioned 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

23 samples harvested; 20 ran; 3 honoured the contract we drafted; 3 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
3ran · our draft was wrong
14ran
3unverified

Licence: 13 of the 23 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

add_task_arguments mk-minchul/AdaFace/config.py found in paper text by Syntology ran MIT (permissive) · 934a10e4aa8e3fc7 · report
all_gather mk-minchul/AdaFace/utils.py found in paper text by Syntology ran MIT (permissive) · 63e31804a718f935 · report
build_head mk-minchul/AdaFace/head.py found in paper text by Syntology ran MIT (permissive) · 43edde19d28891aa · report
calculate_accuracy fdbtrs/ElasticFace/eval/verification.py found in paper text by Syntology ran · honoured contract fingerprinted no licence file found · pointer only · f975336b5d5f1a80 · report
calculate_roc fdbtrs/ElasticFace/eval/verification.py found in paper text by Syntology ran no licence file found · pointer only · 075d6cd5e0436c87 · report
conv1x1 fdbtrs/ElasticFace/backbones/iresnet.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 158bf4c3a5f11f04 · report
conv1x1 fdbtrs/ElasticFace/backbones/utils.py found in paper text by Syntology ran no licence file found · pointer only · 9fd654ad680f6c6e · report
conv3x3 fdbtrs/ElasticFace/backbones/iresnet.py found in paper text by Syntology ran · our draft was wrong no licence file found · pointer only · 29df79c9fdb0cee8 · report
conv3x3 fdbtrs/ElasticFace/backbones/utils.py found in paper text by Syntology ran no licence file found · pointer only · be7e40142c49c8be · report
count_model_flops fdbtrs/ElasticFace/utils/countFLOPS.py found in paper text by Syntology ran no licence file found · pointer only · ddabbebf3d53cffd · report
flops_to_string fdbtrs/ElasticFace/utils/countFLOPS.py found in paper text by Syntology ran no licence file found · pointer only · 79dc6e46e55db7f3 · report
fuse_features_with_norm mk-minchul/AdaFace/utils.py found in paper text by Syntology ran fingerprinted MIT (permissive) · 2f1464d858027854 · report
get_activation_layer fdbtrs/ElasticFace/backbones/activation.py found in paper text by Syntology ran no licence file found · pointer only · 4c9000726845f1ba · report
get_block mk-minchul/AdaFace/net.py found in paper text by Syntology ran · honoured contract fingerprinted MIT (permissive) · ad5dbf57f3ea2633 · report
get_blocks mk-minchul/AdaFace/net.py found in paper text by Syntology ran · honoured contract MIT (permissive) · e82dfb7d2386721b · report
l2_norm fdbtrs/ElasticFace/utils/losses.py found in paper text by Syntology ran · our draft was wrong fingerprinted no licence file found · pointer only · c54fea429589425d · report
l2_norm mk-minchul/AdaFace/utils.py found in paper text by Syntology ran fingerprinted MIT (permissive) · 1aa71e8a5cfa042d · report
make_memmap mk-minchul/AdaFace/evaluate_utils.py found in paper text by Syntology ran MIT (permissive) · 4269ef237488148f · report
round_channels fdbtrs/ElasticFace/backbones/utils.py found in paper text by Syntology ran fingerprinted no licence file found · pointer only · dd12981b28dec323 · report
to_input mk-minchul/AdaFace/inference.py found in paper text by Syntology ran MIT (permissive) · 732bb4b645edf94a · report
build_model mk-minchul/AdaFace/net.py found in paper text by Syntology unverified MIT (permissive) · 5ac43e0b338068fe · report
calculate_val fdbtrs/ElasticFace/eval/verification.py found in paper text by Syntology unverified no licence file found · pointer only · 640d55c5cdb97874 · report
iresnet18 fdbtrs/ElasticFace/backbones/iresnet.py found in paper text by Syntology unverified no licence file found · pointer only · 318ed28c665f6714 · report

Tasks

Adversarial Attack

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