SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.27147 · ICML · 2026

How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance

Nicholas Boffi, Justin Lin, Jerry Huang, Sheel Shah, Kartik Nair

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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, 0 violated it and 0 have no contract verdict; 10 failures of our instrument; 2 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/2604.27147.json · badge: /api/ran/2604.27147.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
jrrhuang/fmrg canonical (classifier label)
classifier basis: census
11 ran · 2 no recorded run
FunctionStatusWhere it lives
add_dual_time_embedder Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/flux_two_timestep/dual_time_embedder.py
pointer only (licence: NOASSERTION) · get_code("6d4f42650f9e79e5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

color2gray Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jrrhuang/fmrg/functions/svd_operators.py
pointer only (licence: NOASSERTION) · get_code("dd9fc69e1eb813b9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

create_clip_preprocess Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/fluxfm_sampler_reward.py
pointer only (licence: NOASSERTION) · get_code("3db7eb2e1b57c45e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

fft2d Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jrrhuang/fmrg/utils/img_util.py
pointer only (licence: NOASSERTION) · get_code("4049ccfc60f88a87")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

gray2color Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/functions/svd_operators.py
pointer only (licence: NOASSERTION) · get_code("6d117fa2c3ad8438")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

normalize Ran
ran, honoured the contract we drafted
jrrhuang/fmrg/utils/img_util.py
pointer only (licence: NOASSERTION) · get_code("e5ef0c9896c821e1")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

random_sq_bbox Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jrrhuang/fmrg/utils/inpaint_util.py
pointer only (licence: NOASSERTION) · get_code("8c38ab1c613539eb")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

register_degradation Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/functions/degradation.py
pointer only (licence: NOASSERTION) · get_code("c864ac145d004e92")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

register_noise Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/functions/measurements.py
pointer only (licence: NOASSERTION) · get_code("905f4b0d3baca742")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

register_operator Ran
ran; our contract draft was wrong, not the code
jrrhuang/fmrg/functions/measurements.py
pointer only (licence: NOASSERTION) · get_code("7f47ba486efd2c7e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

to_np Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jrrhuang/fmrg/utils/img_util.py
pointer only (licence: NOASSERTION) · get_code("a1ab19aa64a8403f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

get_degradation Not yet run
unverified (harvested, no recorded run)
jrrhuang/fmrg/functions/degradation.py
pointer only (licence: NOASSERTION) · get_code("c1dc705cdd55441e")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, jrrhuang/fmrg (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.

get_operator Not yet run
unverified (harvested, no recorded run)
jrrhuang/fmrg/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, jrrhuang/fmrg 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 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 11 are also present in other papers whose code we hold (11 with at least one paper dated earlier, 0 the same month, 0 later) and 2 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
get_operator 10 other papers
10 dated earlier
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
register_operator 9 other papers
9 dated earlier
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
8 dated earlier
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
color2gray 4 other papers
4 dated earlier
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
4 dated earlier
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
fft2d 1 other paper
1 dated earlier
2410.07838 (2024-10)
Minority-Focused Text-to-Image Generation via Prompt Optimization
get_degradation 1 other paper
1 dated earlier
2601.04791 (2026-01)
Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
normalize 1 other paper
1 dated earlier
2410.07838 (2024-10)
Minority-Focused Text-to-Image Generation via Prompt Optimization
random_sq_bbox 1 other paper
1 dated earlier
2405.16749 (2024-05)
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
register_degradation 1 other paper
1 dated earlier
2601.04791 (2026-01)
Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers
to_np 1 other paper
1 dated earlier
2410.07838 (2024-10)
Minority-Focused Text-to-Image Generation via Prompt Optimization

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

In generative modeling, we often wish to produce samples that maximize a user-specified reward such as aesthetic quality or alignment with human preferences, a problem known as guidance. Despite their widespread use, existing guidance methods either require expensive multi-particle, many-step schemes or rely on poorly understood approximations. We reformulate guidance as a deterministic optimal control problem, yielding a hierarchy of algorithms that subsumes existing approaches at the coarsest level. We show that the flow map, an object of significant recent interest for its role in fast inference, arises naturally in the optimal solution. Based on this observation, we propose Flow Map Reward Guidance (FMRG): a training-free, single-trajectory framework that uses the flow map to both integrate and guide the flow. At text-to-image scale, FMRG matches or surpasses baselines across inverse problems and reward-guided generation with as few as 3 NFEs, giving at least an order-of-magnitude speedup in comparison to prior state of the art. Code is available at https://github.com/jrrhuang/fmrg.

For agents

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

get_harvested_code_for_paper("2604.27147")
get_code_for_paper("2604.27147")
have("2604.27147")

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

curl https://syntology.ai/api/ran/2604.27147.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.27147.svg)](https://syntology.ai/paper/2604.27147)

Connect an agent — have() is free.