cs.LGNov 17, 2026

Escaping Latent Traps by Remembering: Training-Free Episodic Kernel Repulsion for World-Model Planning

Authors: Yican Zhao, Bolin Yang, Ruizhe Wang, Haiyang Guo, Fuji Yang, Bingo Wing-Kuen Ling, Zelin Zang

Organizations: Institute of Integrated Circuits and Artificial Intelligence, Qiantang Institute for Advanced Study, Hangzhou, China · Zhejiang University, Hangzhou, China · Guangdong University of Technology, Guangzhou, China

Abstract

Latent world models plan towards a goal image by minimising the distance between predicted and goal latents. This distance is not geodesic: it has local minima, latent traps, behind walls, at corners and in dead ends, and memoryless receding-horizon replanning keeps the agent in them, revisiting states far from the goal. We propose Episodic Kernel Repulsion (EKR), a training-free cost term that penalises candidate plans by a top-kk Gaussian kernel to a novelty-gated memory of the latents the agent has actually visited, rescaled by the current base cost so that its strength is comparable across models. Across two JEPA world models and four benchmarks, EKR raises average success from 31.8% to 46.7% (LeWM) and from 54.7% to 64.0% (H-JEPA) with the same model, planner and budget. Same-memory counterfactuals show that, in most settings, EKR pushes plans away from visited states, in navigation, often at a higher base cost; stuck episodes and revisits drop accordingly. In seven of eight settings it matches or exceeds 4×4\times samples at 0.80.8--1.5×1.5\times compute. Without tuning, it transfers to DINO-WM with CEM: +6.7+6.7 and +19.3+19.3 points on official and longer-goal Wall tasks, and from 44.7% to 100.0% and from 21.0% to 32.0% on long-horizon PointMaze and Push-T.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. MemWM: Associative Memory-Enhanced Latent World Models for Long-Horizon Planning

    Oct 14, 2026Yuwei Sun, Siyu ZhuWorld Model LearningWorld Models for Robotics