SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2601.04791 · ICML · 2026

Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers

Tae-Hyun Oh, Sohwi Lim, Lee Hyoseok, Eunju Cha

arXiv · PDF · Open in the Atlas

Code that ran

18 of 24 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 18 failures of our instrument; 6 no recorded run), measured 2026-11-22; 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/2601.04791.json · badge: /api/ran/2601.04791.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
FlowDPS-Inverse/FlowDPS canonical (classifier label)
classifier basis: census
18 ran · 6 no recorded run
FunctionStatusWhere it lives
CG Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FlowDPS-Inverse/FlowDPS/functions/conjugate_gradient.py
pointer only (licence: NONE) · get_code("dd02f0cf00fbd99c")
How it ran

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

color2gray Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
FlowDPS-Inverse/FlowDPS/functions/svd_operators.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("dd9fc69e1eb813b9")
How it ran

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

compute_alpha Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/svd_ddnm.py
pointer only (licence: NONE) · get_code("9215fb189fbfb9f4")
How it ran

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

dct Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/jpeg.py
pointer only (licence: NONE) · get_code("b15209709fb2b21d")
How it ran

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

estimate_ker Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/utils/admm.py
pointer only (licence: NONE) · get_code("0e658a67281edbbd")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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
FlowDPS-Inverse/FlowDPS/functions/ckpt_util.py
pointer only (licence: NONE) · get_code("d80f2146cfc85e9a")
How it ran

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

gray2color Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/svd_operators.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("6d117fa2c3ad8438")
How it ran

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

inverse_data_transform Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/svd_ddnm.py
pointer only (licence: NONE) · get_code("39ba407e4342bdd3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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
FlowDPS-Inverse/FlowDPS/functions/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, FlowDPS-Inverse/FlowDPS 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.

precompute Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/solve.py
pointer only (licence: NONE) · get_code("8a3063b6376c075d")
How it ran

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

process_prompt_file Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/util.py
pointer only (licence: NONE) · get_code("671ae6f48ea6f086")
How it ran

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

process_text Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/util.py
pointer only (licence: NONE) · get_code("ad6a826eba02ae37")
How it ran

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

register_degradation Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/degradation.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("c864ac145d004e92")
How it ran

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

register_noise Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/measurements.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("905f4b0d3baca742")
How it ran

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

register_operator Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/functions/measurements.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("7f47ba486efd2c7e")
How it ran

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

register_solver Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/sd3_sampler.py
pointer only (licence: NONE); the stored copy get_code serves, from alexdenker/GenRegBench, is pointer only (licence: NONE) · get_code("7d193ace9f177b2f")
How it ran

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

solve_for_k Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/utils/admm.py
pointer only (licence: NONE) · get_code("cfcc80e80bff7714")
How it ran

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

solve_for_k_v2 Ran
ran; our contract draft was wrong, not the code
FlowDPS-Inverse/FlowDPS/utils/admm.py
pointer only (licence: NONE) · get_code("c0954e890f00d83e")
How it ran

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

dct1 Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/functions/jpeg.py
pointer only (licence: NONE) · get_code("9e1d374e9bf8e1fa")
How it ran

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

ddnm_diffusion Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/functions/svd_ddnm.py
pointer only (licence: NONE) · get_code("ad4e0ba376bb7ae7")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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_degradation Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/functions/degradation.py
pointer only (licence: NONE); the stored copy get_code serves, from jrrhuang/fmrg, is pointer only (licence: NOASSERTION) · get_code("c1dc705cdd55441e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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_operator Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/functions/measurements.py
pointer only (licence: NONE); the stored copy get_code serves, from sun-umn/dmplug, is pointer only (licence: NONE) · get_code("bbb1be64bf961d18")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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_solver Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/sd3_sampler.py
pointer only (licence: NONE); the stored copy get_code serves, from alexdenker/GenRegBench, is pointer only (licence: NONE) · get_code("4f078fd69624c31f")
How it ran

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

idct1 Not yet run
unverified (harvested, no recorded run)
FlowDPS-Inverse/FlowDPS/functions/jpeg.py
pointer only (licence: NONE) · get_code("3db7b46e31fd839b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, FlowDPS-Inverse/FlowDPS 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 24 samples lifted from this paper's linked repositories, 24 carry a function identity and 0 do not. Of the 24 distinct functions with an identity, 17 are also present in other papers whose code we hold (15 with at least one paper dated earlier, 0 the same month, 11 later) and 7 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
md5_hash 30 other papers
29 dated earlier, 1 later
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
compute_alpha 23 other papers
22 dated earlier, 1 later · 6 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2102.09672 (2021-02)
Improved Denoising Diffusion Probabilistic Models
2106.06819 (2021-06)
D2C: Diffusion-Denoising Models for Few-shot Conditional Generation
and 20 more not named here
get_operator 10 other papers
9 dated earlier, 1 later
2309.00287 (2023-09)
Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
2403.06054 (2024-03)
Decoupled Data Consistency with Diffusion Purification for Image Restoration
and 7 more not named here
idct1 10 other papers
10 dated earlier
2011.04823 (2020-11)
Language Through a Prism: A Spectral Approach for Multiscale Language Representations
2105.08997 (2021-05)
When Deep Classifiers Agree: Analyzing Correlations between Learning Order and Image Statistics
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
and 7 more not named here
register_operator 9 other papers
8 dated earlier, 1 later
2309.00287 (2023-09)
Fast Diffusion EM: a diffusion model for blind inverse problems with application to deconvolution
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
2403.06054 (2024-03)
Decoupled Data Consistency with Diffusion Purification for Image Restoration
and 6 more not named here
register_noise 8 other papers
7 dated earlier, 1 later
2402.16907 (2024-02)
Diffusion Posterior Proximal Sampling for Image Restoration
2403.06054 (2024-03)
Decoupled Data Consistency with Diffusion Purification for Image Restoration
2403.11407 (2024-03)
Divide-and-Conquer Posterior Sampling for Denoising Diffusion Priors
and 5 more not named here
dct 7 other papers
7 dated earlier
2206.13397 (2022-06)
Generative Modelling With Inverse Heat Dissipation
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
2306.00288 (2023-06)
Training-free Neural Architecture Search for RNNs and Transformers
and 4 more not named here
get_ckpt_path 5 other papers
5 dated earlier
2301.12686 (2023-01)
GibbsDDRM: A Partially Collapsed Gibbs Sampler for Solving Blind Inverse Problems with Denoising Diffusion Restoration
2303.00354 (2023-03)
Unlimited-Size Diffusion Restoration
2312.16519 (2023-12)
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
and 2 more not named here
color2gray 4 other papers
3 dated earlier, 1 later
2303.00354 (2023-03)
Unlimited-Size Diffusion Restoration
2312.16519 (2023-12)
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
2405.10748 (2024-05)
Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
and 1 more not named here
gray2color 4 other papers
3 dated earlier, 1 later
2303.00354 (2023-03)
Unlimited-Size Diffusion Restoration
2312.16519 (2023-12)
Image Restoration by Denoising Diffusion Models with Iteratively Preconditioned Guidance
2405.10748 (2024-05)
Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
and 1 more not named here
ddnm_diffusion 2 other papers
2 dated earlier
2303.00354 (2023-03)
Unlimited-Size Diffusion Restoration
2405.10748 (2024-05)
Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
get_solver 2 other papers
1 dated earlier, 1 later
2410.07838 (2024-10)
Minority-Focused Text-to-Image Generation via Prompt Optimization
2605.10076 (2026-05)
A Stability Benchmark of Generative Regularizers for Inverse Problems
inverse_data_transform 2 other papers
2 dated earlier
2303.00354 (2023-03)
Unlimited-Size Diffusion Restoration
2405.10748 (2024-05)
Deep Data Consistency: a Fast and Robust Diffusion Model-based Solver for Inverse Problems
register_solver 2 other papers
1 dated earlier, 1 later
2410.07838 (2024-10)
Minority-Focused Text-to-Image Generation via Prompt Optimization
2605.10076 (2026-05)
A Stability Benchmark of Generative Regularizers for Inverse Problems
dct1 1 other paper
1 dated earlier
2209.11888 (2022-09)
JPEG Artifact Correction using Denoising Diffusion Restoration Models
get_degradation 1 other paper
1 later
2604.27147 (2026-04)
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
register_degradation 1 other paper
1 later
2604.27147 (2026-04)
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

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

While latent diffusion models (LDMs) have emerged as powerful priors for inverse problems, existing LDM-based solvers frequently suffer from instability. In this work, we first identify the instability as a discrepancy between the solver dynamics and stable reverse diffusion dynamics learned by the diffusion model, and show that reducing this gap stabilizes the solver. Building on this, we introduce Measurement-Consistent Langevin Corrector (MCLC), a theoretically grounded plug-and-play stabilization module that remedies the LDM-based inverse problem solvers through measurement-consistent Langevin updates. Compared to prior approaches that rely on linear manifold assumptions, which often fail to hold in latent space, MCLC provides a principled stabilization mechanism, leading to more stable and reliable behavior in latent space.

For agents

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

get_harvested_code_for_paper("2601.04791")
get_code_for_paper("2601.04791")
have("2601.04791")

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

curl https://syntology.ai/api/ran/2601.04791.json

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

[![Syntology run record](https://syntology.ai/api/ran/2601.04791.svg)](https://syntology.ai/paper/2601.04791)

Connect an agent — have() is free.