Home › Code › edm_sampler

edm_sampler

Syntologyentry name in harvested coderead from the graph 2026-09-24

edm_sampler appears in the code Syntology harvested for 34 papers, as 20 distinct code bodies found in 35 places (a place is one code body under one paper). At least one of them ran in 7 of the papers; 0 of the code bodies carry a behaviour fingerprint.

What this page is not. Routines are grouped here by the exact string of their function or class name. Nothing asserts that two samples named edm_sampler do the same thing, share code, or are comparable; the name is a string, not an identity. Behaviour outputs (what a fingerprinted sample returned on the shared battery) are not in this export and are not shown here; the graph at syntology.ai holds them. "Ran" means executed on a synthesized fixture, not that the code is correct or reproduces a paper.

Samples Syntology

Syntology ran 3 of the 20 distinct code bodies named edm_sampler; 17 are unverified. One tile per status, in the site's fixed vocabulary, each code body counted once:

0ran · honoured contract
0ran · violated contract
2ran · our draft was wrong
1ran · fixture could not drive it
0ran
17unverified
0fingerprinted

Licence is a property of each copy, so it is counted per place: 17 of the 35 places are pointer only (Syntology does not serve that copy's text). This site shows no code text for any sample; every row below links to the file in its repository where the record names one.

“Ran” means the sample executed on a synthesized input; it does not mean the output is correct. “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, and those samples did run. The ran count above is every status except unverified, the same rule as each paper page.

Papers

34 papers shown of 34, newest first; 35 places in the table. A paper with no recorded date is placed by the month its arXiv id encodes, shown in the Date column as YYYY-MM (from id). One row per place: a paper whose repository defines the name more than once appears more than once, and the same code body held for several papers appears once under each, with the same status. Titles and dates are the archive's archive 2025-07-28 for papers in the archive, and the graph's for 5 papers added by Syntology; 1 papers have no page here and are shown by arXiv id only. Status and fingerprint are Syntology's record of each code body; licence is recorded for each place. The File cell ends with the code body's 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.

PaperDateFileStatus SyntologyLicence
A Foundational EDM2-Based Generative Model for High-Resolution Synthetic Fetal Ultrasound Imaging from Open Datasets added by Syntology 2026-08 (from id) xfetus/fetal-ultrasound-edm2/generate_images.py a14db9805bf41197 ran · our draft was wrong no licence file found · pointer only
Towards accurate extreme event likelihoods from diffusion model climate emulators added by Syntology 2026-05 (from id) NVlabs/cBottle/src/cbottle/diffusion_samplers.py b8f910a033c16972 unverified Apache-2.0 (permissive)
How I Met Your Bias: Investigating Bias Amplification in Diffusion Models added by Syntology 2025-12 (from id) NVlabs/edm/generate.py 8b16b0674af254db unverified no licence file found · pointer only
InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames added by Syntology 2025-10 (from id) HaoruiLi46/InertialAR/InertialAR/diffusion_loss.py 5410f612607c88fc unverified no licence file found · pointer only
Local Mechanisms of Compositional Generalization in Conditional Diffusion added by Syntology 2025-09 (from id) NVlabs/edm2/generate_images.py a14db9805bf41197 ran · our draft was wrong no licence file found · pointer only
Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation 11 Jun 2025 Zyriix/GDD/generate.py 77de35b318b043bc unverified MIT (permissive)
A Theory for Conditional Generative Modeling on Multiple Data Sources 20 Feb 2025 ml-gsai/multi-source-gm/real_world_experiments/generate_images.py a14db9805bf41197 ran · our draft was wrong MIT (permissive)
REG: Rectified Gradient Guidance for Conditional Diffusion Models 31 Jan 2025 zhengqigao/REG/EDMv2/generate_images.py 27ca4582511b7d38 ran · fixture could not drive it MIT (permissive)
Memorization and Regularization in Generative Diffusion Models 27 Jan 2025 baptistar/DiffusionModelDynamics/RectangleImages/generate.py 8b16b0674af254db unverified MIT (permissive)
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models 9 Dec 2024 reds-lab/restricted_gradient_diversity_unlearning/CIFAR/generate.py 8b16b0674af254db unverified no licence file found · pointer only
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure 31 Oct 2024 Morefre/Understanding-Generalizability-of-Diffusion-Models-Requires-Rethinking-the-Hidden-Gaussian-Structure/generate.py 8b16b0674af254db unverified no licence file found · pointer only
Diffusion Models Learn Low-Dimensional Distributions via Subspace Clustering 4 Sep 2024 identical code first harvested elsewhere 00dcc1be26a2af0f unverified licence of this copy not recorded
Guiding a Diffusion Model with a Bad Version of Itself 4 Jun 2024 nvlabs/edm2/generate_images.py a14db9805bf41197 ran · our draft was wrong licence not identified · pointer only
Guiding a Diffusion Model with a Bad Version of Itself 4 Jun 2024 dopplerchase/cira-diff/cira_diff/edm.py 6afde01dd97af6ea unverified licence not identified · pointer only
SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation 28 May 2024 sony/soundctm/tango_edm/models_edm.py 8b16b0674af254db unverified MIT (permissive)
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models 11 Apr 2024 kynkaat/guidance-interval/sampling/edm_sampler.py a1b475ef1c3f3263 unverified Apache-2.0 (permissive)
Training Unbiased Diffusion Models From Biased Dataset 2 Mar 2024 alsdudrla10/TIW-DSM/generate.py 8b16b0674af254db unverified no licence file found · pointer only
Label-Noise Robust Diffusion Models 27 Feb 2024 byeonghu-na/tdsm/generate.py 3b64dcecdee0a7f5 unverified Apache-2.0 (permissive)
A Good Score Does not Lead to A Good Generative Model 10 Jan 2024 sixuli/ddpm_and_kde/src/DiffMemorize/generate_optim.py 8add76eac47fd8ce unverified no licence file found · pointer only
Analyzing and Improving the Training Dynamics of Diffusion Models 5 Dec 2023 identical code first harvested elsewhere a14db9805bf41197 ran · our draft was wrong licence of this copy not recorded
The Emergence of Reproducibility and Generalizability in Diffusion Models 8 Oct 2023 huijieZH/Diffusion-Model-Generalizability/edm/generate.py 00dcc1be26a2af0f unverified MIT (permissive)
Observation-Guided Diffusion Probabilistic Models 6 Oct 2023 junoh-kang/ogdm_edm/generate.py abcc7581cc4b80ec unverified licence not identified · pointer only
On Memorization in Diffusion Models 4 Oct 2023 sail-sg/DiffMemorize/generate_edm.py 8b16b0674af254db unverified MIT (permissive)
Mirror Diffusion Models for Constrained and Watermarked Generation 2 Oct 2023 ghliu/mdm/generate_watermark.py 8b16b0674af254db unverified Apache-2.0 (permissive)
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis 4 Sep 2023 THUDM/RelayDiffusion/generate_imagenet.py 00ad7cd5515a96f8 unverified Apache-2.0 (permissive)
Fast Training of Diffusion Models with Masked Transformers 15 Jun 2023 anima-lab/maskdit/sample.py d84d2d3b03445f34 unverified MIT (permissive)
Fast Diffusion Model 12 Jun 2023 sail-sg/fdm/generate.py 8b16b0674af254db unverified Apache-2.0 (permissive)
Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models 25 Apr 2023 Zhendong-Wang/Patch-Diffusion/generate.py 9f88bec60fdc8cf7 unverified Apache-2.0 (permissive)
A Recipe for Watermarking Diffusion Models 17 Mar 2023 yunqing-me/watermarkdm/edm/generate.py 8b16b0674af254db unverified MIT (permissive)
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models 8 Feb 2023 newbeeer/pfgmpp/generate.py 1a497dc67152411a ran · our draft was wrong licence not identified · pointer only
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models 1 Feb 2023 newbeeer/stf/generate.py 4fa854e489f921db unverified no licence file found · pointer only
3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models 26 Jan 2023 1zb/3dshape2vecset/models_class_cond.py b657cfb7a6465cbc unverified MIT (permissive)
Elucidating the Design Space of Diffusion-Based Generative Models 1 Jun 2022 identical code first harvested elsewhere 8b16b0674af254db unverified licence of this copy not recorded
Equivariant Diffusion for Molecule Generation in 3D 31 Mar 2022 yuanzhi-zhu/mini_edm/train_edm.py 3e4b3a16b7841ced unverified no licence file found · pointer only
arXiv:Xia_Rectified_Diffusion_Guidance_for_Conditional_Generation_CVPR_2025_paper thuxmf/recfg/generate_images.py 53d8885663cb864c unverified MIT (permissive)

This site shows no code text; each File cell links to the file on GitHub at the repository's current default branch, which may have changed since the 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 cell for the reason. Per-sample records for a paper are on its paper page under "Code Syntology ran".

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