I am a first-year Physics PhD student at MIT and IAIFI, advised by Prof. Max Tegmark. I have interned at Microsoft Research Asia. Before that, I received my Bachelor's degree in physics from Peking University. Prior to that, my memories are sealed in my hometown, Wuhan.
I research on the intersection of artificial intelligence and physics in general. My research interests include: (1) AI for physics: extracting physical insights (e.g. conservation laws and symmetries) from data, improving prediction accuracy and sampling efficiency for data analysis in physics; (2) Physics for AI: developing effective theories to understand the dynamics and generalization of neural networks. Besides that, I am generally interested in applications of AI to chemistry, biology, vision, language, medicine and robotics. I am happy and open to any form of collaboration.
I love music and mobile photography in my leisure time, but also have great fun thinking about (somewhat philosophical) questions regarding the boundary (if any) between human & artificial intelligence, mathematical modeling of humanities and other nerdy stuff.
Machine-Learning Non-Conservative Dynamics for New-Physics Detection (Ziming Liu, Bohan Wang, Meng Qi, Wei Chen, Max Tegmark and Tie-Yan Liu)
Comment: We present Neural New-Physics Detector (NNPhD), a machine learning algorithm for decomposing conservative and non-conservative forces. NNPhD is a natural extension of Lagrangian Neural Network.
AI Poincaré: Machine Learning Conservation Laws from Trajectories. (Ziming Liu and Max Tegmark)
Comment: We present AI Poincaré, a machine learning algorithm for auto-discovering conserved quantities using trajectory data from unknown dynamical systems. We released our code on PyPI here, and you could simply install aipoincare package by typing in
pip install aipoincare.
Ziming Liu. All rights reserved. Design: HTML5 UP