SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00633 · 2024

Improving GFlowNets for Text-to-Image Diffusion Alignment

arXiv · PDF · Open in the Atlas

Code that ran

6 of 8 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; 6 failures of our instrument; 2 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/2406.00633.json · badge: /api/ran/2406.00633.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
apple/ml-diffusion-alignment-gflownet canonical (classifier label)
classifier basis: census
6 ran · 2 no recorded run
FunctionStatusWhere it lives
aesthetic_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
apple/ml-diffusion-alignment-gflownet/alignment/rewards.py
pointer only (licence: NOASSERTION) · get_code("def436565d510e61")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

compute_snr Ran
ran; our contract draft was wrong, not the code
apple/ml-diffusion-alignment-gflownet/alignment/diffusers_patch/ddim_with_logprob.py
pointer only (licence: NONE) · get_code("16309f96889a07a1")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, apple/ml-diffusion-alignment-gflownet 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.

image_postprocess Ran
ran; our contract draft was wrong, not the code
apple/ml-diffusion-alignment-gflownet/alignment/utils.py
pointer only (licence: NOASSERTION) · get_code("1e0be34763ee5d94")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

jpeg_compressibility Ran
ran; our contract draft was wrong, not the code
apple/ml-diffusion-alignment-gflownet/alignment/rewards.py
pointer only (licence: NOASSERTION) · get_code("f574e43d805c92b6")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

jpeg_incompressibility Ran
ran; our contract draft was wrong, not the code
apple/ml-diffusion-alignment-gflownet/alignment/rewards.py
pointer only (licence: NOASSERTION) · get_code("1a27d7f753b72eb8")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

read_csv Ran
ran; our contract draft was wrong, not the code
apple/ml-diffusion-alignment-gflownet/alignment/prompts.py
pointer only (licence: NOASSERTION) · get_code("62776a64bdbedd3b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

ddim_step_with_logprob Not yet run
unverified (harvested, no recorded run)
apple/ml-diffusion-alignment-gflownet/alignment/diffusers_patch/ddim_with_logprob.py
pointer only (licence: NOASSERTION) · get_code("0e8c6806652348a9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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.

pred_orig_latent Not yet run
unverified (harvested, no recorded run)
apple/ml-diffusion-alignment-gflownet/alignment/diffusers_patch/ddim_with_logprob.py
pointer only (licence: NOASSERTION) · get_code("edcd1f489e641901")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-diffusion-alignment-gflownet (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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 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
compute_snr 9 other papers
4 dated earlier, 4 later, 1 undated
2311.17918 (2023-11)
Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving
2403.10094 (2024-03)
RangeLDM: Fast Realistic LiDAR Point Cloud Generation
2403.12931 (2024-03)
You Only Sample Once: Taming One-Step Text-To-Image Synthesis by Self-Cooperative Diffusion GANs
and 6 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

Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as alignment to a text description, which can be specified with a black-box reward function. Prior works fine-tune pretrained diffusion models to achieve this goal through reinforcement learning-based algorithms. Nonetheless, they suffer from issues including slow credit assignment as well as low quality in their generated samples. In this work, we explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability -- a natural scenario for the framework of generative flow networks (GFlowNets). To this end, we propose the Diffusion Alignment with GFlowNet (DAG) algorithm to post-train diffusion models with black-box property functions. Extensive experiments on Stable Diffusion and various reward specifications corroborate that our method could effectively align large-scale text-to-image diffusion models with given reward information.

For agents

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

get_harvested_code_for_paper("2406.00633")
get_code_for_paper("2406.00633")
have("2406.00633")

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

curl https://syntology.ai/api/ran/2406.00633.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.00633.svg)](https://syntology.ai/paper/2406.00633)

Connect an agent — have() is free.