Learning Commute-Time-Preserving World Models for Planning

arXiv:2610.01373 · cs.LG · Submitted 2026-10-01 · Read on arXiv

cs.LG

Submitted: 2026-10-01

Updated: 2026-10-01

Project page: https://ctwm-website.github.io

Terminology

• World Model — 1× in this paper · explained in 7 episodes

Sources

• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Layer Normalization
• LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
• VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning
• Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
• Temporal Difference Flows
• Compositional Planning with Jumpy World Models
• World Models
• Dreamer-CDP: Improving Reconstruction-free World Models Via Continuous Deterministic Representation Prediction
• stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels
• Understanding Self-Supervised Learning via Latent Distribution Matching
• Representation Learning with Contrastive Predictive Coding
• Laplacian Representations for Decision-Time Planning
• DeepMind Control Suite
• Reachability-Aware Laplacian Representation in Reinforcement Learning
• Temporal Straightening for Latent Planning
• The Laplacian in RL: Learning Representations with Efficient Approximations
• Sub-JEPA: Subspace Gaussian Regularization for Stable End-to-End World Models
• Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks