SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2405.17673 · NeurIPS · 2024

Fast Samplers for Inverse Problems in Iterative Refinement Models

Stephan Mandt, Ruihan Yang, Kushagra Pandey

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 5 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/2405.17673.json · badge: /api/ran/2405.17673.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
mandt-lab/c-pigdm canonical (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
NVlabs/RED-diff canonical (classifier label)
classifier basis: census
1 ran · 1 no recorded run
gnobitab/RectifiedFlow community
Papers with Code archive
2 ran · 0 no recorded run
mandt-lab/ci2rm marked official in Papers with Code
Papers with Code archive
1 ran · 0 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
Conjugate Ran
ran on a synthesized input · constructed an object; no result was computed
mandt-lab/ci2rm/flow/sampler.py
pointer only (licence: NONE) · get_code("401b0f6645e0528f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mandt-lab/ci2rm 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.

center_crop_arr Ran
ran; our contract draft was wrong, not the code
NVlabs/RED-diff/datasets/imagenet.py
pointer only (licence: NOASSERTION) · get_code("d96f46caebdb91c0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/RED-diff (NOASSERTION). 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.

from_flattened_numpy Ran
ran; our contract draft was wrong, not the code
gnobitab/RectifiedFlow/ImageGeneration/sampling.py
pointer only (licence: NONE) · get_code("84f1005930b04eee")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, gnobitab/RectifiedFlow 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_optimizer Ran
ran; our contract draft was wrong, not the code
mandt-lab/c-pigdm/flow/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("8ff7c24dade9904c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mandt-lab/c-pigdm 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_rectified_flow_sampler Ran
ran; our contract draft was wrong, not the code
gnobitab/RectifiedFlow/ImageGeneration/sampling.py
pointer only (licence: NONE) · get_code("4b3dc148a2e2a2e6")
How it ran

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

optimization_manager Ran
ran; our contract draft was wrong, not the code
mandt-lab/c-pigdm/flow/losses.py
pointer only (licence: NONE); the stored copy get_code serves, from hfmei/idc, is pointer only (licence: NONE) · get_code("366bb8c7035a2fc8")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mandt-lab/c-pigdm 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.

to_flattened_numpy Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from klightz/PSF
pointer only · get_code("d0bdb81d2cb8c3e7")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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_imagenet_loader Not yet run
unverified (harvested, no recorded run)
NVlabs/RED-diff/datasets/imagenet.py
pointer only (licence: NOASSERTION) · get_code("6e6c81454ec88afd")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, NVlabs/RED-diff (NOASSERTION). 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 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 2 the same month, 4 later) and 4 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
optimization_manager 16 other papers
13 dated earlier, 1 the same month, 2 later
2106.05527 (2021-06)
Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
and 13 more not named here
get_optimizer 15 other papers
12 dated earlier, 1 the same month, 2 later
2110.05243 (2021-10)
Score-based diffusion models for accelerated MRI
2205.01490 (2022-05)
Subspace Diffusion Generative Models
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
and 12 more not named here
to_flattened_numpy
brick of this paper's assembly: helper
5 other papers
3 dated earlier, 2 later · 1 only as an assembly brick
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
2212.01747 (2022-12)
Fast Point Cloud Generation with Straight Flows
2401.02032 (2024-01)
DiffusionEdge: Diffusion Probabilistic Model for Crisp Edge Detection
and 2 more not named here
from_flattened_numpy
brick of this paper's assembly: helper
4 other papers
2 dated earlier, 2 later · 1 only as an assembly brick
2209.12753 (2022-09)
On Investigating the Conservative Property of Score-Based Generative Models
2212.01747 (2022-12)
Fast Point Cloud Generation with Straight Flows
2410.00983 (2024-10)
Robust Guided Diffusion for Offline Black-Box Optimization
and 1 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

Constructing fast samplers for unconditional diffusion and flow-matching models has received much attention recently; however, existing methods for solving inverse problems, such as super-resolution, inpainting, or deblurring, still require hundreds to thousands of iterative steps to obtain high-quality results. We propose a plug-andplay framework for constructing efficient samplers for inverse problems, requiring only pre-trained diffusion or flow-matching models. We present Conditional Conjugate Integrators, which leverage the specific form of the inverse problem to project the respective conditional diffusion/flow dynamics into a more amenable space for sampling. Our method complements popular posterior approximation methods for solving inverse problems using diffusion/flow models. We evaluate the proposed method's performance on various linear image restoration tasks across multiple datasets, employing diffusion and flow-matching models. Notably, on challenging inverse problems like 4× super-resolution on the ImageNet dataset, our method can generate high-quality samples in as few as 5 conditional sampling steps and outperforms competing baselines requiring 20-1000 steps. Our code will be publicly available at https://github.com/mandt-lab/c-pigdm.

For agents

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

get_harvested_code_for_paper("2405.17673")
get_code_for_paper("2405.17673")
have("2405.17673")

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

curl https://syntology.ai/api/ran/2405.17673.json

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

[![Syntology run record](https://syntology.ai/api/ran/2405.17673.svg)](https://syntology.ai/paper/2405.17673)

Connect an agent — have() is free.