3 papers
cs.LG2026
Terminally constrained flow-based generative models from an optimal control perspective
Weiguo Gao, Ming Li, Qianxiao Li
We address the problem of sampling from terminally constrained distributions with pre-trained flow-based generative models through an optimal control formulation. Theoretically, we…
cs.LG2025
Learning task-specific predictive models for scientific computing
Jianyuan Yin, Qianxiao Li
We consider learning a predictive model to be subsequently used for a given downstream task (described by an algorithm) that requires access to the model evaluation. This task need…
math.DS2024
Non-intrusive model combination for learning dynamical systems
Shiqi Wu, Ludovic Chamoin, Qianxiao Li
In data-driven modelling of complex dynamic processes, it is often desirable to combine different classes of models to enhance performance. Examples include coupled models of diffe…