SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.08946 · 2024

Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training

arXiv · PDF · Open in the Atlas

Code that ran

12 of 19 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 failures of our instrument; 7 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.08946.json · badge: /api/ran/2407.08946.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
yunshuwu/ContrastiveDiffusionLoss canonical (classifier label)
classifier basis: census
12 ran · 7 no recorded run
FunctionStatusWhere it lives
Normalize Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/network_arch/ema_ddpm_unet.py
pointer only (licence: NONE); the stored copy get_code serves, from Xingyu-Zheng/BiDM, is pointer only (licence: NONE) · get_code("c3a6b977022957cb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/dnnlib/util.py
pointer only (licence: NONE) · get_code("674eca7b9e1b6439")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

format_time_brief Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/dnnlib/util.py
pointer only (licence: NONE) · get_code("32af001972a0699f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_ckpt_path Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/ckpt_util.py
pointer only (licence: NONE) · get_code("d3d30f649b83beae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_ddpm_schedule Ran
ran, honoured the contract we drafted
yunshuwu/ContrastiveDiffusionLoss/utils.py
pointer only (licence: NONE) · get_code("4a8b7eda64bac8b1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_timestep_embedding Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
yunshuwu/ContrastiveDiffusionLoss/network_arch/ema_ddpm_unet.py
pointer only (licence: NONE) · get_code("cb49209c125de1b4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

logistic_integrate Ran
ran, honoured the contract we drafted
yunshuwu/ContrastiveDiffusionLoss/utils.py
pointer only (licence: NONE) · get_code("4e2ebe7dd3aa1d85")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

logsnr_uniform_selector Ran
ran, honoured the contract we drafted
yunshuwu/ContrastiveDiffusionLoss/utils.py
pointer only (licence: NONE) · get_code("3dfb3d007332417e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

md5_hash Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/ckpt_util.py
pointer only (licence: NONE); the stored copy get_code serves, from zh460045050/V2L-Tokenizer, is pointer only (licence: NONE) · get_code("07d90bd6ae1be7db")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

nonlinearity Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/network_arch/ema_ddpm_unet.py
pointer only (licence: NONE) · get_code("3137073275f8c21a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

prepreation_karras Ran
ran; our contract draft was wrong, not the code
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/seq_samplers.py
pointer only (licence: NONE) · get_code("54a1664f139dc5e9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sample_fn_ddpm Ran
ran, honoured the contract we drafted
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/seq_samplers.py
pointer only (licence: NONE) · get_code("26e89fe4f7a4342f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ask_yes_no Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/dnnlib/util.py
pointer only (licence: NONE) · get_code("9d31d2c4cd16bb2d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parasam_forward Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/_para_samplers.py
pointer only (licence: NONE) · get_code("a09285676a1aca60")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parasam_forward Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/para_samplers.py
pointer only (licence: NONE) · get_code("52b472cd0e155aa1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parasam_forward Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/para_samplers_visualization.py
pointer only (licence: NONE) · get_code("bb3944742c2d662a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parasam_forward_mmd Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/para_samplers.py
pointer only (licence: NONE) · get_code("709391ce90e2c2c5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

parasam_forward_mmd Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/para_samplers_visualization.py
pointer only (licence: NONE) · get_code("b9df12d4cc178f7b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

sample_fn_karras Not yet run
unverified (harvested, no recorded run)
yunshuwu/ContrastiveDiffusionLoss/diffusion_models/seq_samplers.py
pointer only (licence: NONE) · get_code("501d3dd1ed3f35a2")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, yunshuwu/ContrastiveDiffusionLoss when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 19 samples lifted from this paper's linked repositories, 19 carry a function identity and 0 do not. Of the 19 distinct functions with an identity, 7 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 7 the same month, 7 later) and 12 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
nonlinearity 156 other papers
88 dated earlier, 6 the same month, 58 later, 4 same year, order not determinable · 25 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 153 more not named here
get_timestep_embedding 91 other papers
65 dated earlier, 6 the same month, 16 later, 4 same year, order not determinable · 7 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 88 more not named here
Normalize 90 other papers
58 dated earlier, 5 the same month, 24 later, 3 same year, order not determinable · 32 only as an assembly brick
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2106.00132 (2021-06)
On Fast Sampling of Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 87 more not named here
format_time 73 other papers
41 dated earlier, 2 the same month, 29 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 70 more not named here
ask_yes_no 69 other papers
41 dated earlier, 2 the same month, 25 later, 1 undated
2004.00049 (2020-04)
In-Domain GAN Inversion for Real Image Editing
2004.11660 (2020-04)
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
and 66 more not named here
format_time_brief 68 other papers
37 dated earlier, 2 the same month, 28 later, 1 undated
2108.00946 (2021-08)
StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators
2202.00273 (2022-02)
StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets
2206.07695 (2022-06)
VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids
and 65 more not named here
md5_hash 30 other papers
20 dated earlier, 1 the same month, 8 later, 1 same year, order not determinable
2008.01777 (2020-08)
Making Sense of CNNs: Interpreting Deep Representations & Their Invariances with INNs
2104.07652 (2021-04)
Geometry-Free View Synthesis: Transformers and no 3D Priors
2112.00384 (2021-12)
Exploration into Translation-Equivariant Image Quantization
and 27 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion models learn to denoise data and the trained denoiser is then used to generate new samples from the data distribution. In this paper, we revisit the diffusion sampling process and identify a fundamental cause of sample quality degradation: the denoiser is poorly estimated in regions that are far Outside Of the training Distribution (OOD), and the sampling process inevitably evaluates in these OOD regions. This can become problematic for all sampling methods, especially when we move to parallel sampling which requires us to initialize and update the entire sample trajectory of dynamics in parallel, leading to many OOD evaluations. To address this problem, we introduce a new self-supervised training objective that differentiates the levels of noise added to a sample, leading to improved OOD denoising performance. The approach is based on our observation that diffusion models implicitly define a log-likelihood ratio that distinguishes distributions with different amounts of noise, and this expression depends on denoiser performance outside the standard training distribution. We show by diverse experiments that the proposed contrastive diffusion training is effective for both sequential and parallel settings, and it improves the performance and speed of parallel samplers significantly.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.08946")
get_code_for_paper("2407.08946")
have("2407.08946")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.08946.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.08946.svg)](https://syntology.ai/paper/2407.08946)

Connect an agent — have() is free.