I’m Lingxiao Wang(王 凌霄), now a Research Scientist（研究員） in RIKEN-iTHEMS (理化学研究所 数理創造研究センター). My research interest includes Machine Learning in Physics (especially high energy nuclear physics, e.g., QCD Matter, Lattice QCD, etc.), Collective Behavior and Atomspheric Sciences.

Now, I’m the main facilitator of a working group of “DEEP-IN” in RIKEN-iTHEMS, which aims to develop deep learning models for solving inverse problems in sciences.

I have organized many “machine learning physics” seminars for physicists online, find the previous activities in our page MLP club. If you are seeking any form of academic cooperation, please feel free to contact me via lingxiaowang[at]foxmail.com.

🔥 News

• 2025.08.25 - 09.05:  ✈️✈️ I was invited to attend the “Build Big or Build Smart: Examining Scale and Domain Knowledge in Machine Learning for Fundamental Physics” Workshop at Munich Institute for Astro-, Particle and BioPhysics(MIAPbP), Germany.

• 2025.08.17 - 08.20:  🚆🚆 I was invited to give a lecture in 第三届量子场论前沿研讨会(the 3rd Workshop on Frontiers of Quantum Field Theory) at Guiyang, China.

• 2025.07:  🎉🎉 I was approved to start a new position as Assistant Professor in the Instite of Physics Intelligence(iPI) at the UTokyo from November 2025 under the support of “JST-BOOST Program 次世代AI人材育成プログラム（若手研究者支援））”.

• 2025.02 - 2025.05:  👶 I was in Parental Leave for my child.

• 2025.03:  🎉🎉 I was awarded a new grant “QCD物理の逆問題を解くための物理駆動型深層学習” in 学術変革領域研究（Ａ）- 公募研究 from 文部科学省科学研究費補助金.

• 2025.01:  🎉🎉 Our review paper “Physics-Driven Learning for Inverse Problems in Quantum Chromodynamics” got publihsed on “ Nature Reviews Physics”. It provides a structured and concise overview of how incorporating prior knowledge such as symmetry, continuity and equations into deep learning designs can address diverse inverse problems across different physical sciences.

• 2024.12:  🎉🎉 Our work “Higher-order cumulants in diffusion models” got the Best ‘Physics for AI’ Paper Award (Sponsored by Apple) in “Machine Learning and the Physical Sciences” Workshop at the 38th conference on Neural Information Processing Systems (NeurIPS), December 15, 2024.