[Submitted on 12 Mar 2026 (
[v1](https://arxiv.org/abs/2603.12231v1)), last revised 11 Aug 2026 (this version, v3)]
[View PDF](https://arxiv.org/pdf/2603.12231)
[HTML (experimental)](https://arxiv.org/html/2603.12231v3)
Abstract:Learning good representations is essential for latent planning with world models. While pretrained visual encoders produce strong semantic visual features, they are not tailored to planning and contain information irrelevant -- or even detrimental -- to planning. Inspired by the perceptual straightening hypothesis in human visual processing, we introduce temporal straightening to improve representation learning for latent planning. Using a curvature regularizer that encourages locally straightened latent trajectories, we jointly learn an encoder and a predictor of a Joint-Embedding Predictive Architecture (JEPA) world model. We show that reducing curvature this way makes the Euclidean distance in latent space a better proxy for the geodesic distance and improves the conditioning of the planning objective. We demonstrate empirically that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks. Our code is available at this https URL.
Submission history #
From: Ying Wang [
[view email](https://arxiv.org/show-email/f61b8959/2603.12231)]
**Thu, 12 Mar 2026 17:49:47 UTC (3,528 KB)**
[\[v1\]](https://arxiv.org/abs/2603.12231v1)
**Thu, 11 Jun 2026 22:12:49 UTC (3,547 KB)**
[\[v2\]](https://arxiv.org/abs/2603.12231v2)
**[v3]** Tue, 11 Aug 2026 05:38:52 UTC (3,496 KB)
References & Citations
...
Bibliographic Explorer
(What is the Explorer?) Connected Papers
(What is Connected Papers?) Litmaps
(What is Litmaps?) scite Smart Citations
(What are Smart Citations?) alphaXiv
(What is alphaXiv?) CatalyzeX Code Finder for Papers
(What is CatalyzeX?) DagsHub
(What is DagsHub?) Gotit.pub
(What is GotitPub?) Hugging Face
(What is Huggingface?) ScienceCast
(What is ScienceCast?) Influence Flower
(What are Influence Flowers?) CORE Recommender
(What is CORE?) IArxiv Recommender
(What is IArxiv?) 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.