Abductive World Modeling via Causal Representation Learning

arXiv:2609.36985 · cs.LG, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Comments: 21 pages, 4 figures

Code: https://github.com/baiz-tech/AWM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Representation Learning — 1× in this paper · explained in 2 episodes

Sources

• Invariant Risk Minimization
• V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
• Revisiting Feature Prediction for Learning Visual Representations from Video
• World Models
• Orca: The World is in Your Mind

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