Skip to content
AI News HubLIVE
Original source2 min read

Spectral-Target Physical Latent Structuring for JEPA-Style World Models

Summary

This paper identifies a new failure mode in latent world models called physical representation laziness, which can persist even when representation collapse is prevented. The authors introduce a lightweight Fourier auxiliary head that imposes physically informed structure on the latent space at training time with no inference-time cost, improving planning success rates—especially in dynamic and low-data environments.

SourcearXiv Machine LearningAuthor: Penghao Zhu, Salvatore Penachio, Kaustav Mukherjee, Aneesh Jonelagadda
Spectral-Target Physical Latent Structuring for JEPA-Style World Models
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 2 Sep 2026]

Title:Spectral-Target Physical Latent Structuring for JEPA-Style World Models

View a PDF of the paper titled Spectral-Target Physical Latent Structuring for JEPA-Style World Models, by Penghao Zhu and 3 other authors

View PDF HTML (experimental)

Abstract:Latent world models have become increasingly popular as a method to predict and plan in latent space rather than pixel space. Recent architectures, such as LeWorldModel (LeWM), jointly train the encoder and predictor using regularization techniques like SIGReg to prevent representation collapse. Even with such regularization preventing representation collapse, we identify a new world model failure mode of \textit{physical representation laziness}, particularly noted in highly dynamic environments. For these lazy cases, the learned latent states do not collapse but nonetheless fail to represent key physical properties, causing ubiquitous downstream planning failure. To resolve this issue, we propose training-time auxiliary supervision with a lightweight "Fourier auxiliary head", which enforces physically-informed structuring of the latent space with no additional inference-time cost and can be generalized to any environment. Experimentally, we show that the auxiliary head substantially improves planning success rates in dynamic environments where the baseline LeWM exhibits physical representation laziness. It also leads to modest improvements in other environments, even when the baseline does not exhibit physical representation laziness. We further observe superior planning performance being accompanied by higher latent space correlations with key physical properties, indicating both the ability of our method to physically structure latent states and the potential planning-side benefit to the learned representation being physically structured. We also see in low-data regimes, auxiliary supervision is particularly impactful in increasing success rate. These findings support the use of our Fourier auxiliary head method to improve both overall success rate and data efficiency, while avoiding representation laziness in latent world models.

Comments: 9 pages, 4 figures

Subjects:

Machine Learning (cs.LG)

Cite as: arXiv:2609.04264 [cs.LG]

(or arXiv:2609.04264v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.04264

arXiv-issued DOI via DataCite

Submission history

From: Aneesh Jonelagadda [view email] [v1] Wed, 2 Sep 2026 18:05:06 UTC (5,171 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Spectral-Target Physical Latent Structuring for JEPA-Style World Models, by Penghao Zhu and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Physical representation laziness can emerge in latent world models even when regularization prevents representation collapse.
  • A lightweight Fourier auxiliary head adds physical structuring to the latent space during training without extra inference cost.
  • Experiments show substantial gains in dynamic environments and low-data regimes, together with stronger correlations between latent states and key physical properties.

Highlights and analysis are generated automatically and may contain errors. Check the original source.