Assessing generative modeling approaches for free energy estimates in condensed matter

ArXi:2512.23930v2 Announce Type: replace-cross The accurate estimation of free energy differences between two states is a long-standing challenge in molecular simulations. Traditional approaches generally rely on sampling multiple intermediate states to ensure sufficient overlap in phase space and are, consequently, computationally expensive. Boltzmann Generators and related generative-model-based methods have recently addressed this challenge by learning a direct probability density transform between two states.