Minimum-Excess-Work Guidance

ICLR 2026 Conference Submission18459 Authors

Keywords: guidance, generative modeling, statistical mechanics

TL;DR: A physics-inspired framework to guide generative models towards sampling rare molecular states or matching experimental data by using thermodynamic work as regularization.

Abstract: We propose a regularization framework inspired by thermodynamic work for guiding pre-trained probability flow generative models (e.g., continuous normalizing flows or diffusion models) by minimizing excess work, a concept rooted in statistical mechanics and with strong conceptual connections to optimal transport. Our approach enables efficient guidance in sparse-data regimes common to scientific applications, where only limited target samples or partial density constraints are available. We introduce two strategies: Path Guidance, which facilitates sampling of rare transition states by concentrating probability mass on user-defined subsets, and Observable Guidance, which aligns generated distributions with experimental observables while preserving entropy. We demonstrate the framework’s versatility on two coarse-grained protein models, highlighting its ability to sample transition configurations and to correct systematic biases using experimental data. The method bridges thermodynamic principles with modern generative architectures, offering a principled, efficient, and physics-inspired alternative to standard fine-tuning in data-scarce domains. Empirical results highlight improved sample efficiency and bias reduction, underscoring its applicability to molecular simulations and beyond.

Primary Area: applications to physical sciences (physics, chemistry, biology, etc.)

Submission Number: 18459