2024

January 14, New Paper PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Laws is now on arXiv. This paper shows how a single ICON model can make forward and reverse predictions for different PDEs with different strides, and generalize well to PDEs with new forms, without any fine-tuning.

2023

November 11-12, Event I will attend International Workshop on Recent Developments in Applied Mathematics and its Applications at Caltech. Looking forward to meeting old and new friends!

September 19, Publication In-Context Operator Learning with Data Prompts for Differential Equation Problems (code) is now published on Proceedings of the National Academy of Sciences (PNAS). Thanks to all the co-authors and reviewers!

August 9, New Paper Fine-Tune Language Models as Multi-Modal Differential Equation Solvers is now on arXiv. This paper significantly improves the ICON model and evolves it into multi-modal learning. (It was originally titled “Prompting In-Context Operator Learning with Sensor Data, Equations, and Natural Language”, but we changed the title for clarity.)

May 28 – June 3, Event I will join the American Mathematical Society’s Mathematics Research Communities Program.

May 14, Talk I will be giving a talk on stochastic/interactive particle dynamic inference at the SIAM Conference on Applications of Dynamical Systems in Portland, Oregon.

April 17, New Paper In-Context Operator Learning for Differential Equation Problems is now on arXiv. This paper draws inspiration from large language models and proposes a promising approach, namely In-Context Operator Networks (ICON), to build large models for scientific machine learning.

2022

July 1, Appointment I will join the Department of Mathematics at UCLA as an Assistant Adjunct Professor, working with Prof. Stanley Osher.