Papers › Diffusion Models With Learned Adaptive Noise

Diffusion Models With Learned Adaptive Noise

20 Dec 2023arXiv:2312.13236archive 2025-07-28

Subham Sekhar Sahoo, Aaron Gokaslan, Chris De Sa, Volodymyr Kuleshov

Diffusion models have gained traction as powerful algorithms for synthesizing high-quality images. Central to these algorithms is the diffusion process, a set of equations which maps data to noise in a way that can significantly affect performance. In this paper, we explore whether the diffusion process can be learned from data. Our work is grounded in Bayesian inference and seeks to improve log-likelihood estimation by casting the learned diffusion process as an approximate variational posterior that yields a tighter lower bound (ELBO) on the likelihood. A widely held assumption is that the ELBO is invariant to the noise process: our work dispels this assumption and proposes multivariate learned adaptive noise (MULAN), a learned diffusion process that applies noise at different rates across an image. Specifically, our method relies on a multivariate noise schedule that is a function of the data to ensure that the ELBO is no longer invariant to the choice of the noise schedule as in previous works. Empirically, MULAN sets a new state-of-the-art in density estimation on CIFAR-10 and ImageNet and reduces the number of training steps by 50%. We provide the code, along with a blog post and video tutorial on the project page: https://s-sahoo.com/MuLAN

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="2312.13236")

Code

Syntology Ran 12 of 14 code samples harvested from 2 repositories linked to this paper; 2 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · violated contract; 1 ran · our draft was wrong; 9 ran with no contract checked.

By repository: official repository: 11 samples from 1 repository, 10 ran; community: 1 sample from 1 repository, 0 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

s-sahoo/mulan officialmentioned in papermentioned on GitHubjaxApache-2.0 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

14 samples harvested; 12 ran; 1 honoured the contract we drafted; 2 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.

1ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
9ran
2unverified

Licence: 3 of the 14 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. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

calculate_blur_radius s-sahoo/mulan/ldm/dataset.py official repository ran Apache-2.0 (permissive) · 0b78680501c709aa · report
conditional_decorator s-sahoo/mulan/ldm/model_vdm.py official repository ran Apache-2.0 (permissive) · d949d0d0bc5e63bc · report
copy_dict s-sahoo/mulan/ldm/experiment.py official repository ran Apache-2.0 (permissive) · d741dec5707d4fea · report
dist s-sahoo/mulan/ldm/utils.py official repository ran Apache-2.0 (permissive) · 4ff86972ab4194f5 · report
generate_image_grids s-sahoo/mulan/ldm/utils.py official repository ran Apache-2.0 (permissive) · 3f7ef732a2045c0f · report
get_ode_likelihood_fn s-sahoo/mulan/ldm/notebook_utils.py official repository ran Apache-2.0 (permissive) · fca1c8baa8ecba65 · report
get_timestep_embedding s-sahoo/mulan/ldm/model_vdm.py official repository ran Apache-2.0 (permissive) · 6f3e290aea3952fb · report
inner_prod s-sahoo/MuLAN/ldm/model_mulan_velocity.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 28c1cf9c76e7e3b4 · report
restore_partial s-sahoo/mulan/ldm/experiment.py official repository ran Apache-2.0 (permissive) · 428176833658e89d · report
sigmoid s-sahoo/mulan/ldm/model_vdm.py official repository ran Apache-2.0 (permissive) · ce72b6af52c249b8 · report
allgather_and_reshape s-sahoo/mulan/ldm/utils.py official repository unverified Apache-2.0 (permissive) · 4c25c1400cdbb0a1 · report
load_model_from_config measure-infinity/mulan-code/scripts/pipeline_sdxl.py community unverified no licence file found · pointer only · 92ee6d3bae662baa · report
chunk identical code first harvested elsewhere ran · our draft was wrong licence of this copy not recorded · 8241c0562bc710fd · report
numpy_to_pil identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · 1e63d588563eb90a · report

Tasks

Bayesian InferenceDensity EstimationImage Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation CIFAR-10 MULAN NLL (bits/dim) 2.55 #2 of 15 Archive leaderboard report
Density Estimation ImageNet 32x32 MuLAN NLL (bits/dim) 3.67 #1 of 5 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

DiffusionSET

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