SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.14217 · 2022

Diffusion-LM Improves Controllable Text Generation

arXiv · PDF · Open in the Atlas

Code that ran

11 of 12 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; 3 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 8 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/2205.14217.json · badge: /api/ran/2205.14217.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
xiangli1999/diffusion-lm canonical (classifier label)
classifier basis not recorded on the link
10 ran · 1 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
approx_standard_normal_cdf Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/improved_diffusion/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cfd76fd0d89574a4")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from quandao10/slct, and GitHub detected no licence in that repository 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.

discretized_gaussian_log_likelihood Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/improved_diffusion/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from quandao10/slct, is pointer only (licence: NONE) · get_code("cd33283d615fb3d7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from quandao10/slct, and GitHub detected no licence in that repository 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.

generate_samples Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/control_gen/baseline_control.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("bd70407415c5ed19")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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.

levenshteinDistance Ran
ran, honoured the contract we drafted
xiangli1999/diffusion-lm/improved-diffusion/control_gen/eval_control.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("ee1169ece28e0d9d")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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.

load_results_simple Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/anlg_infill/mbr_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("6690b1379e201b37")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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.

make_master_params Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/improved_diffusion/fp16_util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from freemasti/diffo, is pointer only (licence: NONE) · get_code("a863803cdd5f3ce6")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from freemasti/diffo, and GitHub detected no licence in that repository 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.

mbr Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/anlg_infill/mbr_eval.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("23e6db3ffd64425a")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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.

normal_kl Ran
ran, honoured the contract we drafted
xiangli1999/diffusion-lm/improved-diffusion/improved_diffusion/losses.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from facebookresearch/agrol, is pointer only (licence: NOASSERTION) · get_code("cf2798b666b231ca")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from facebookresearch/agrol, and GitHub could not classify the licence of that repository (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.

parse_resume_step_from_filename Ran
ran, honoured the contract we drafted
this paper's copy was not recorded; identical code first harvested from zzzhangboya/scoreopt
pointer only; the stored copy get_code serves, from zzzhangboya/scoreopt, is pointer only (licence: NONE) · get_code("76313eaf1a6e8f2a")
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.

remove_leaves Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/control_gen/baseline_control.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("8fc7161a00ae39b0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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.

unflatten_master_params Ran
ran; our contract draft was wrong, not the code
xiangli1999/diffusion-lm/improved-diffusion/improved_diffusion/fp16_util.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from freemasti/diffo, is pointer only (licence: NONE) · get_code("30e43bcf12d042b0")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from freemasti/diffo, and GitHub detected no licence in that repository 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.

generate_samples_from_scratch Not yet run
unverified (harvested, no recorded run)
xiangli1999/diffusion-lm/improved-diffusion/control_gen/baseline_control.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from deno-v/tgm-dlm, is pointer only (licence: NONE) · get_code("cc6bf6f3b1388227")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from deno-v/tgm-dlm, and GitHub detected no licence in that repository 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 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 12 are also present in other papers whose code we hold (7 with at least one paper dated earlier, 3 the same month, 12 later) and 0 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
normal_kl 160 other papers
11 dated earlier, 1 the same month, 148 later · 19 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 157 more not named here
approx_standard_normal_cdf 154 other papers
11 dated earlier, 1 the same month, 142 later · 17 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 151 more not named here
discretized_gaussian_log_likelihood 128 other papers
11 dated earlier, 1 the same month, 116 later · 16 only as an assembly brick
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2105.05233 (2021-05)
Diffusion Models Beat GANs on Image Synthesis
2111.11672 (2021-11)
Few-shot Image Generation with Mixup-based Distance Learning
and 125 more not named here
parse_resume_step_from_filename 18 other papers
2 dated earlier, 16 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2111.14818 (2021-11)
Blended Diffusion for Text-driven Editing of Natural Images
2206.07696 (2022-06)
Diffusion Models for Video Prediction and Infilling
and 15 more not named here
make_master_params 16 other papers
1 dated earlier, 15 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2206.07696 (2022-06)
Diffusion Models for Video Prediction and Infilling
2209.08725 (2022-09)
Neural Wavelet-domain Diffusion for 3D Shape Generation
and 13 more not named here
unflatten_master_params 15 other papers
1 dated earlier, 14 later
2010.02502 (2020-10)
Denoising Diffusion Implicit Models
2206.07696 (2022-06)
Diffusion Models for Video Prediction and Infilling
2209.08725 (2022-09)
Neural Wavelet-domain Diffusion for 3D Shape Generation
and 12 more not named here
levenshteinDistance 2 other papers
1 dated earlier, 1 later
1805.07820 (2018-05)
Targeted Adversarial Examples for Black Box Audio Systems
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
generate_samples 1 other paper
1 later
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
generate_samples_from_scratch 1 other paper
1 later
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
load_results_simple 1 other paper
1 later
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
mbr 1 other paper
1 later
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model
remove_leaves 1 other paper
1 later
2402.13040 (2024-02)
Text-Guided Molecule Generation with Diffusion Language Model

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

Controlling the behavior of language models (LMs) without re-training is a major open problem in natural language generation. While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there has been little progress on complex, fine-grained controls (e.g., syntactic structure). To address this challenge, we develop a new non-autoregressive language model based on continuous diffusions that we call Diffusion-LM. Building upon the recent successes of diffusion models in continuous domains, Diffusion-LM iteratively denoises a sequence of Gaussian vectors into word vectors, yielding a sequence of intermediate latent variables. The continuous, hierarchical nature of these intermediate variables enables a simple gradient-based algorithm to perform complex, controllable generation tasks. We demonstrate successful control of Diffusion-LM for six challenging fine-grained control tasks, significantly outperforming prior work.

For agents

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

get_harvested_code_for_paper("2205.14217")
get_code_for_paper("2205.14217")
have("2205.14217")

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

curl https://syntology.ai/api/ran/2205.14217.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.14217.svg)](https://syntology.ai/paper/2205.14217)

Connect an agent — have() is free.