SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.10404 · 2024

Explaining generative diffusion models via visual analysis for interpretable decision-making process

arXiv · PDF · Open in the Atlas

Code that ran

8 of 11 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; 1 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 4 failures of our instrument; 3 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/2402.10404.json · badge: /api/ran/2402.10404.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
ian-jihoonpark/X-Diffusion canonical (classifier label)
classifier basis: census
8 ran · 3 no recorded run
FunctionStatusWhere it lives
contrastive_loss Ran
ran; our contract draft was wrong, not the code
ian-jihoonpark/X-Diffusion/models/clip_encoder.py
pointer only (licence: NONE); the stored copy get_code serves, from microsoft/xpretrain, is pointer only (licence: NOASSERTION) · get_code("4675779aec92d6c0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

downsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ian-jihoonpark/X-Diffusion/models/resenet_blocks.py
pointer only (licence: NONE) · get_code("f46bcb6099334fa6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

gkern Ran
ran, honoured the contract we drafted
ian-jihoonpark/X-Diffusion/utils.py
pointer only (licence: NONE) · get_code("b4550bba38cdca07")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

has_arg Ran
ran, violated the contract we drafted
ian-jihoonpark/X-Diffusion/utils.py
pointer only (licence: NONE) · get_code("da06038052820fb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

normal_auc Ran
ran, violated the contract we drafted
ian-jihoonpark/X-Diffusion/DF-CAM_auc.py
pointer only (licence: NONE) · get_code("a2eedc61e21e9deb")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

set_seed Ran
ran; our contract draft was wrong, not the code
ian-jihoonpark/X-Diffusion/DF-CAM_auc.py
pointer only (licence: NONE) · get_code("92a70b0298648379")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

upfirdn2d_native Ran
ran on a synthesized input
ian-jihoonpark/X-Diffusion/models/resenet_blocks.py
pointer only (licence: NONE) · get_code("d3ea46d2b896a593")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

upsample_2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ian-jihoonpark/X-Diffusion/models/resenet_blocks.py
pointer only (licence: NONE) · get_code("31e7ed79c46ee9a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

auto_device Not yet run
unverified (harvested, no recorded run)
ian-jihoonpark/X-Diffusion/DF-CAM_auc.py
pointer only (licence: NONE) · get_code("ee533eed6c7d4440")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

clip_loss Not yet run
unverified (harvested, no recorded run)
ian-jihoonpark/X-Diffusion/models/clip_encoder.py
pointer only (licence: NONE); the stored copy get_code serves, from PeterGriffinJin/InstructG2I, is pointer only (licence: NONE) · get_code("f2ca34eca05d40cd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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.

get_class_name Not yet run
unverified (harvested, no recorded run)
ian-jihoonpark/X-Diffusion/utils.py
pointer only (licence: NONE) · get_code("8d547cd400589a27")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ian-jihoonpark/X-Diffusion 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 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 4 later) and 5 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
contrastive_loss 27 other papers
10 dated earlier, 16 later, 1 same year, order not determinable · 3 only as an assembly brick
2206.00621 (2022-06)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training
2209.06430 (2022-09)
CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment
2210.00312 (2022-10)
Multimodal Analogical Reasoning over Knowledge Graphs
and 24 more not named here
clip_loss 16 other papers
3 dated earlier, 12 later, 1 same year, order not determinable · 1 only as an assembly brick
2305.13050 (2023-05)
AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation
2306.02583 (2023-06)
Stable Diffusion is Unstable
2309.16429 (2023-09)
Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation
and 13 more not named here
downsample_2d 7 other papers
5 dated earlier, 2 later
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
and 4 more not named here
upsample_2d 7 other papers
5 dated earlier, 2 later
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2304.06720 (2023-04)
Expressive Text-to-Image Generation with Rich Text
2307.10422 (2023-07)
PreDiff: Precipitation Nowcasting with Latent Diffusion Models
and 4 more not named here
has_arg 2 other papers
2 dated earlier
2106.07875 (2021-06)
S-LIME: Stabilized-LIME for Model Explanation
2311.15722 (2023-11)
GLIME: General, Stable and Local LIME Explanation
upfirdn2d_native 2 other papers
2 dated earlier
2303.09535 (2023-03)
FateZero: Fusing Attentions for Zero-shot Text-based Video Editing
2310.01107 (2023-10)
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models

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 have demonstrated remarkable performance in generation tasks. Nevertheless, explaining the diffusion process remains challenging due to it being a sequence of denoising noisy images that are difficult for experts to interpret. To address this issue, we propose the three research questions to interpret the diffusion process from the perspective of the visual concepts generated by the model and the region where the model attends in each time step. We devise tools for visualizing the diffusion process and answering the aforementioned research questions to render the diffusion process human-understandable. We show how the output is progressively generated in the diffusion process by explaining the level of denoising and highlighting relationships to foundational visual concepts at each time step through the results of experiments with various visual analyses using the tools. Throughout the training of the diffusion model, the model learns diverse visual concepts corresponding to each time-step, enabling the model to predict varying levels of visual concepts at different stages. We substantiate our tools using Area Under Cover (AUC) score, correlation quantification, and cross-attention mapping. Our findings provide insights into the diffusion process and pave the way for further research into explainable diffusion mechanisms.

For agents

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

get_harvested_code_for_paper("2402.10404")
get_code_for_paper("2402.10404")
have("2402.10404")

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

curl https://syntology.ai/api/ran/2402.10404.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.10404.svg)](https://syntology.ai/paper/2402.10404)

Connect an agent — have() is free.