SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.03349 · 2024

Image Inpainting via Tractable Steering of Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 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; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 4 failures of our instrument; 1 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/2401.03349.json · badge: /api/ran/2401.03349.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
ucla-starai/tiramisu canonical (classifier label)
classifier basis: census
6 ran · 1 no recorded run
FunctionStatusWhere it lives
construct_divisions Ran
ran; our contract draft was wrong, not the code
ucla-starai/tiramisu/controlled_img_modeling/img_based_structures/shared_pd.py
pointer only (licence: NONE) · get_code("732fba0548da35e1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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_activation Ran
ran; our contract draft was wrong, not the code
ucla-starai/tiramisu/controlled_img_modeling/latent_transformer_2d/attention.py
pointer only (licence: NONE) · get_code("de254adf0261a4e3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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_prod_lls Ran
ran; our contract draft was wrong, not the code
ucla-starai/tiramisu/controlled_img_modeling/lvd/apply_lvd.py
pointer only (licence: NONE) · get_code("d3fcbed7ad4cbcae")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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.

log_1_min_a Ran
ran, honoured the contract we drafted
ucla-starai/tiramisu/controlled_img_modeling/latent_transformer_2d/diffusion_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from MuhangTian/TimeDiff, is pointer only (licence: NONE) · get_code("479771b269fc5883")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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.

log_add_exp Ran
ran, honoured the contract we drafted
ucla-starai/tiramisu/controlled_img_modeling/latent_transformer_2d/diffusion_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from MuhangTian/TimeDiff, is pointer only (licence: NONE) · get_code("032c0dece6594020")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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.

sum_except_batch Ran
ran; our contract draft was wrong, not the code
ucla-starai/tiramisu/controlled_img_modeling/latent_transformer_2d/diffusion_transformer.py
pointer only (licence: NONE); the stored copy get_code serves, from MuhangTian/TimeDiff, is pointer only (licence: NONE) · get_code("5eb945b1f970f6af")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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_sum_lls Not yet run
unverified (harvested, no recorded run)
ucla-starai/tiramisu/controlled_img_modeling/lvd/apply_lvd.py
pointer only (licence: NONE) · get_code("ec6863a54e565926")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ucla-starai/tiramisu 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 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 4 later) and 3 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
log_add_exp 14 other papers
12 dated earlier, 2 later · 3 only as an assembly brick
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2205.16007 (2022-05)
Improved Vector Quantized Diffusion Models
and 11 more not named here
log_1_min_a 13 other papers
12 dated earlier, 1 later · 3 only as an assembly brick
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2205.16007 (2022-05)
Improved Vector Quantized Diffusion Models
and 10 more not named here
sum_except_batch 9 other papers
8 dated earlier, 1 later · 2 only as an assembly brick
2102.05379 (2021-02)
Argmax Flows and Multinomial Diffusion: Learning Categorical Distributions
2205.16007 (2022-05)
Improved Vector Quantized Diffusion Models
and 6 more not named here
get_activation 2 other papers
1 dated earlier, 1 later
1701.07204 (2017-01)
Fast Exact k-Means, k-Medians and Bregman Divergence Clustering in 1D
Dai_SeaS_Few-shot_Industrial_Anomaly_Image_Generation_with_Separation_and_Sharing_ICCV_2025_paper (2025 (year only))
SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning

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 are the current state of the art for generating photorealistic images. Controlling the sampling process for constrained image generation tasks such as inpainting, however, remains challenging since exact conditioning on such constraints is intractable. While existing methods use various techniques to approximate the constrained posterior, this paper proposes to exploit the ability of Tractable Probabilistic Models (TPMs) to exactly and efficiently compute the constrained posterior, and to leverage this signal to steer the denoising process of diffusion models. Specifically, this paper adopts a class of expressive TPMs termed Probabilistic Circuits (PCs). Building upon prior advances, we further scale up PCs and make them capable of guiding the image generation process of diffusion models. Empirical results suggest that our approach can consistently improve the overall quality and semantic coherence of inpainted images across three natural image datasets (i.e., CelebA-HQ, ImageNet, and LSUN) with only $\sim\! 10 \%$ additional computational overhead brought by the TPM. Further, with the help of an image encoder and decoder, our method can readily accept semantic constraints on specific regions of the image, which opens up the potential for more controlled image generation tasks. In addition to proposing a new framework for constrained image generation, this paper highlights the benefit of more tractable models and motivates the development of expressive TPMs.

For agents

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

get_harvested_code_for_paper("2401.03349")
get_code_for_paper("2401.03349")
have("2401.03349")

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

curl https://syntology.ai/api/ran/2401.03349.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.03349.svg)](https://syntology.ai/paper/2401.03349)

Connect an agent — have() is free.