Stable and Counterfactually Robust Physical World Models from Imposed Structure and Learned Physics
cs.LG
Submitted: 2026-09-24
Updated: 2026-09-24
Terminology
Sources
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- Training Compute-Optimal Large Language Models
- Causal-JEPA: Learning World Models through Object-Level Latent Masking
- Dissipative Hamiltonian Neural Networks: Learning Dissipative and Conservative Dynamics Separately
- Dissipative SymODEN: Encoding Hamiltonian Dynamics with Dissipation and Control into Deep 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