[2602.00797] Zero-Flow Encoders

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Statistics > Machine Learning

arXiv:2602.00797 (stat)

[Submitted on 31 Jan 2026 (v1), last revised 7 Jun 2026 (this version, v3)]

Title:Zero-Flow Encoders

Authors:Yakun Wang, Leyang Wang, Song Liu, Taiji Suzuki<br>View a PDF of the paper titled Zero-Flow Encoders, by Yakun Wang and 2 other authors

View PDF<br>HTML (experimental)

Abstract:Flow-based methods have achieved significant success in various generative modeling tasks, capturing nuanced details within complex data distributions. However, few existing works have exploited this unique capability to resolve fine-grained structural details beyond generation tasks. This paper presents a flow-inspired framework for representation learning. First, we demonstrate that a rectified flow trained using independent coupling is zero everywhere at $t=0.5$ if and only if the source and target distributions are identical. We term this property the \emph{zero-flow criterion}. Second, we show that this criterion can certify conditional independence, thereby extracting \emph{sufficient information} from the data. Third, we translate this criterion into a tractable, simulation-free loss function that enables learning amortized Markov blankets in graphical models and latent representations in self-supervised learning tasks. Experiments on both simulated and real-world datasets demonstrate the effectiveness of our approach. The code reproducing our experiments can be found at: this https URL.

Comments:<br>Yakun Wang and Leyang Wang contributed equally to this work; As published at ICML 2026

Subjects:

Machine Learning (stat.ML); Machine Learning (cs.LG)

Cite as:<br>arXiv:2602.00797 [stat.ML]

(or<br>arXiv:2602.00797v3 [stat.ML] for this version)

https://doi.org/10.48550/arXiv.2602.00797

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Yakun Wang [view email]<br>[v1]<br>Sat, 31 Jan 2026 16:11:01 UTC (6,198 KB)

[v2]<br>Thu, 4 Jun 2026 16:53:55 UTC (3,466 KB)

[v3]<br>Sun, 7 Jun 2026 16:59:20 UTC (3,466 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Zero-Flow Encoders, by Yakun Wang and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

stat.ML

next >

new<br>recent<br>| 2026-02

Change to browse by:

cs<br>cs.LG<br>stat

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .

Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)

Major funding support from