Temporal Straightening for Latent Planning
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 dis...
| Authors | Ying Wang, Oumayma Bounou, Gaoyue Zhou et al. |
|---|---|
| Primary category | cs.LG |
| Published | 12 March 2026 |
| Last updated at source | 11 August 2026 |
Connected in the knowledge graph
- agentic-learning-ai-lab/point_maze_mediumDataset · cited by
Models and datasets referencing this paper
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.