Identifiable World Models from Pretrained Diffusion Representations

arXiv:2610.07028 · cs.LG · Submitted 2026-10-04 · Read on arXiv

cs.LG

Submitted: 2026-10-04

Updated: 2026-10-04

Code: https://github.com/pollen-robotics/microduck_rl

Terminology

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

Sources

• CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
• World Models
• Mastering Diverse Domains through World Models
• Representation Learning with Contrastive Predictive Coding

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