AI RESEARCH
Excluding the Target Domain Improves Extrapolation: Deconfounded Hierarchical Physics Constraints
arXiv CS.AI
•
ArXi:2605.07485v1 Announce Type: cross Extrapolation to out-of-distribution conditions is a fundamental challenge for physics-constrained deep generative models. Existing methods apply physical constraints as a single static regularization term uniformly across the generation process, and address neither the hierarchical structure of physical laws and the confounding variable problem.