Temporal Straightening for Latent Planning

Researchers Ying Wang and colleagues introduced temporal straightening, a curvature regularizer that encourages locally straightened latent trajectories in a Joint-Embedding Predictive Architecture (JEPA) world model, according to a paper submitted to arXiv on 12 March 2026 and last revised 11 August 2026 (v3). The method jointly learns an encoder and predictor, making Euclidean distance in latent space a better proxy for geodesic distance and improving the conditioning of the planning objective. The authors report that temporal straightening makes gradient-based planning more stable and yields significantly higher success rates across a suite of goal-reaching tasks, with code available at agenticlearning.ai/temporal-straightening.

Computer Science Machine Learning Submitted on 12 Mar 2026 v1 https://arxiv.org/abs/2603.12231v1 , last revised 11 Aug 2026 this version, v3 Title:Temporal Straightening for Latent Planning 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 https://agenticlearning.ai/temporal-straightening . 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 Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender IArxiv Recommender What is IArxiv? https://iarxiv.org/about 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 https://info.arxiv.org/labs/index.html .