7 papers
Stochastic and Non-local Closure Modeling for Nonlinear Dynamical Systems via Latent Score-based Generative Models
Xinghao Dong, Huchen Yang, Jin-Long Wu
We propose a latent score-based generative AI framework for learning stochastic, non-local closure models and constitutive laws in nonlinear dynamical systems of computational mech…
Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems
Huchen Yang, Xinghao Dong, Dan Negrut +1
Optimizing the communication structure of large language model based multi-agent systems (LLM-MAS) has been shown to improve downstream performance and reduce token usage. Existing…
Bayesian experimental design: grouped geometric pooled posterior via ensemble Kalman methods
Huchen Yang, Xinghao Dong, Jinlong Wu
Bayesian experimental design (BED) for complex physical systems is often limited by the nested inference required to estimate the expected information gain (EIG) or its gradients.…
Synergizing Transport-Based Generative Models and Latent Geometry for Stochastic Closure Modeling
Xinghao Dong, Huchen Yang, Jin-long Wu
Diffusion models recently developed for generative AI tasks can produce high-quality samples while still maintaining diversity among samples to promote mode coverage, providing a p…
Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback--Leibler Divergence and Wasserstein Distance
Huchen Yang, Xinghao Dong, Jin-Long Wu
Designing experiments that systematically gather data from complex physical systems is central to accelerating scientific discovery. While Bayesian experimental design (BED) provid…
Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
Huchen Yang, Xinghao Dong, Jin-Long Wu
Bayesian experimental design (BED) offers a principled framework for optimizing data acquisition by leveraging probabilistic inference. However, practical implementations of BED ar…