SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2604.20041 · ICML · 2026

Normalizing Flows with Iterative Denoising

Jiatao Gu, David Berthelot, Tianrong Chen, Shuangfei Zhai, Joshua Susskind

arXiv · PDF · Open in the Atlas

Code that ran

6 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (4 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 3 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/2604.20041.json · badge: /api/ran/2604.20041.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-itarflow community
Papers with Code archive
6 ran · 3 no recorded run
FunctionStatusWhere it lives
AttentionBlock Ran
ran on a synthesized input · constructed an object; no result was computed
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("2a16a09ac7673248")
How it ran

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

FourierTimeEmbedding Ran
ran on a synthesized input · constructed an object; no result was computed
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("0a8044ad2effad89")
How it ran

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

MLP Ran
ran on a synthesized input · constructed an object; no result was computed
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("b8e9fe82a45f2393")
How it ran

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

Permutation Ran
ran on a synthesized input · constructed an object; no result was computed
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("4c94cc59ab9d74ac")
How it ran

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

PermutationFlip Ran
ran on a synthesized input
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("0cd60472b465ce1d")
How it ran

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

PermutationIdentity Ran
ran on a synthesized input
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("f833161486682bc7")
How it ran

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

Attention Not yet run
unverified (harvested, no recorded run)
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("7753ed9874d5cbbd")
How it ran

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

MetaBlock Not yet run
unverified (harvested, no recorded run)
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("6179ab0684b1def9")
How it ran

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

Model Not yet run
unverified (harvested, no recorded run)
apple/ml-itarflow/transformer_flow.py
pointer only (licence: NOASSERTION) · get_code("3005c6918fa3e19f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, apple/ml-itarflow (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 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 4 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 3 later) and 5 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
MLP
brick of this paper's assembly: model
2 other papers
1 dated earlier, 1 later · 2 only as an assembly brick
1601.06759 (2016-01)
Pixel Recurrent Neural Networks Aäron van den Oord
2605.31063 (2026-05)
Free energy Estimation on Any State Space
PermutationFlip
brick of this paper's assembly: model
2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
1601.06759 (2016-01)
Pixel Recurrent Neural Networks Aäron van den Oord
2605.07193 (2026-05)
Coupling Models for One-Step Discrete Generation
PermutationIdentity
brick of this paper's assembly: model
2 other papers
1 dated earlier, 1 later · 1 only as an assembly brick
1601.06759 (2016-01)
Pixel Recurrent Neural Networks Aäron van den Oord
2605.07193 (2026-05)
Coupling Models for One-Step Discrete Generation
Permutation
brick of this paper's assembly: model
1 other paper
1 dated earlier · 1 only as an assembly brick
1601.06759 (2016-01)
Pixel Recurrent Neural Networks Aäron van den Oord

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

Normalizing Flows (NFs) are a classical family of likelihood-based methods that have received revived attention. Recent efforts such as TARFlow have shown that NFs are capable of achieving promising performance on image modeling tasks, making them viable alternatives to other methods such as diffusion models. In this work, we further advance the state of Normalizing Flow generative models by introducing iterative TARFlow (iTARFlow). Unlike diffusion models, iTARFlow maintains a fully end-to-end, likelihood-based objective during training. During sampling, it performs autoregressive generation followed by an iterative denoising procedure inspired by diffusion-style methods. Through extensive experiments, we show that iTARFlow achieves competitive performance across Ima-geNet resolutions of 64, 128, and 256 pixels, demonstrating its potential as a strong generative model and advancing the frontier of Normalizing Flows. In addition, we analyze the characteristic artifacts produced by iTARFlow, offering insights that may shed light on future improvements. Code is available at https:// github.com/apple/ml-itarflow.

For agents

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

get_harvested_code_for_paper("2604.20041")
get_code_for_paper("2604.20041")
have("2604.20041")

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

curl https://syntology.ai/api/ran/2604.20041.json

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

[![Syntology run record](https://syntology.ai/api/ran/2604.20041.svg)](https://syntology.ai/paper/2604.20041)

Connect an agent — have() is free.