Latent-Space Planning

Latest papers

31 papers13 papers in the last four weeks, up 225% on the four weeks before. 0.1% of all new papers.

Temporal Straightening for Latent Planning
Mar 12, 2026Ying Wang, Oumayma Bounou, Gaoyue Zhou +4Latent-Space Planning World Model-Based Planning
New York University · Brown University · University of Toronto

Mar 12, 2026J/K move · Enter open · S save

Temporal Straightening for Latent Planning

Ying Wang, Oumayma Bounou, Gaoyue Zhou, Randall Balestriero+3

New York University · Brown University · University of Toronto

Latent-Space Planning World Model-Based Planning Trajectory Representation Learning Joint-Embedding Predictive Architecture

Open paper AskPDF arXiv

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 https://agenticlearning.ai/temporal-straightening.