SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.05098 · NeurIPS · 2024

Improved off-policy training of diffusion samplers

Yoshua Bengio, Minsu Kim, Marcin Sendera

arXiv · PDF · Open in the Atlas

Code that ran

15 of 17 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; 14 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/2402.05098.json · badge: /api/ran/2402.05098.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
GFNOrg/gfn-diffusion canonical (classifier label)
classifier basis: census
15 ran · 2 no recorded run
FunctionStatusWhere it lives
adjust_ld_step Ran
ran, honoured the contract we drafted
GFNOrg/gfn-diffusion/energy_sampling/langevin.py
pointer only (licence: NONE) · get_code("5bf80298d705eb51")
How it ran

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

bwd_tb Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/gflownet_losses.py
pointer only (licence: NONE) · get_code("da64b9cc0cb5f420")
How it ran

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

collate Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/buffer.py
pointer only (licence: NONE) · get_code("b12c326f37f6b931")
How it ran

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

collate Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/vae/buffer.py
pointer only (licence: NONE) · get_code("8758016c1e97eb30")
How it ran

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

dcp Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/utils.py
pointer only (licence: NONE) · get_code("7a713c0355a39fa4")
How it ran

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

fwd_tb Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/vae/gflownet_losses.py
pointer only (licence: NONE) · get_code("371d2c191597088e")
How it ran

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

fwd_tb_avg Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/gflownet_losses.py
pointer only (licence: NONE) · get_code("aed2af6e29d0346b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GFNOrg/gfn-diffusion 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_figure Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GFNOrg/gfn-diffusion/energy_sampling/plot_utils.py
pointer only (licence: NONE) · get_code("7d2f988fc32e4ecd")
How it ran

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

langevin_dynamics Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/langevin.py
pointer only (licence: NONE) · get_code("e02c1b1c37c66258")
How it ran

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

linear_mmd2 Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/sample_metrics.py
pointer only (licence: NONE) · get_code("bb890357a4a87c70")
How it ran

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

logmeanexp Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/utils.py
pointer only (licence: NONE) · get_code("cded7f5b04d3ed38")
How it ran

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

poly_mmd2 Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GFNOrg/gfn-diffusion/energy_sampling/sample_metrics.py
pointer only (licence: NONE) · get_code("9970f30509d9c6ff")
How it ran

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

viz_many_well Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/plot_utils.py
pointer only (licence: NONE) · get_code("3952c49c556847d5")
How it ran

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

viz_sample2d Ran
ran; our contract draft was wrong, not the code
GFNOrg/gfn-diffusion/energy_sampling/plot_utils.py
pointer only (licence: NONE) · get_code("c564a15078fe1e13")
How it ran

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

wasserstein Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
GFNOrg/gfn-diffusion/energy_sampling/sample_metrics.py
pointer only (licence: NONE) · get_code("48975d6f9511eaee")
How it ran

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

cal_subtb_coef_matrix Not yet run
unverified (harvested, no recorded run)
GFNOrg/gfn-diffusion/energy_sampling/utils.py
pointer only (licence: NONE) · get_code("ac941abcdd9c5845")
How it ran

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

fwd_tb Not yet run
unverified (harvested, no recorded run)
GFNOrg/gfn-diffusion/energy_sampling/gflownet_losses.py
pointer only (licence: NONE) · get_code("1022ab51101ead2b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, GFNOrg/gfn-diffusion 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 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 distinct functions with an identity, 5 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 4 later) and 12 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
linear_mmd2 3 other papers
3 later
2403.00999 (2024-03)
Distributional Dataset Distillation with Subtask Decomposition
2407.11734 (2024-07)
Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
2410.04386 (2024-10)
Data Distribution Valuation
wasserstein 3 other papers
1 the same month, 2 later
2402.03207 (2024-02)
Light and Optimal Schrödinger Bridge Matching
2405.14449 (2024-05)
Adversarial Schrödinger Bridge Matching
2410.12456 (2024-10)
Training Neural Samplers with Reverse Diffusive KL Divergence
poly_mmd2 2 other papers
2 later
2403.00999 (2024-03)
Distributional Dataset Distillation with Subtask Decomposition
2407.11734 (2024-07)
Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
cal_subtb_coef_matrix 1 other paper
1 dated earlier
2310.02679 (2023-10)
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
logmeanexp 1 other paper
1 later
2409.09787 (2024-09)
BNEM: A Boltzmann Sampler Based on Bootstrapped Noised Energy Matching

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

We study the problem of training diffusion models to sample from a distribution with a given unnormalized density or energy function. We benchmark several diffusion-structured inference methods, including simulation-based variational approaches and off-policy methods (continuous generative flow networks). Our results shed light on the relative advantages of existing algorithms while bringing into question some claims from past work. We also propose a novel exploration strategy for off-policy methods, based on local search in the target space with the use of a replay buffer, and show that it improves the quality of samples on a variety of target distributions. Our code for the sampling methods and benchmarks studied is made public at (link) as a base for future work on diffusion models for amortized inference.

For agents

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

get_harvested_code_for_paper("2402.05098")
get_code_for_paper("2402.05098")
have("2402.05098")

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

curl https://syntology.ai/api/ran/2402.05098.json

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

[![Syntology run record](https://syntology.ai/api/ran/2402.05098.svg)](https://syntology.ai/paper/2402.05098)

Connect an agent — have() is free.