ComENet: Towards complete and efficient message passing for 3D molecular graphs

L Wang, Y Liu, Y Lin, H Liu, S Ji - Advances in Neural …, 2022 - proceedings.neurips.cc
Many real-world data can be modeled as 3D graphs, but learning representations that
incorporates 3D information completely and efficiently is challenging. Existing methods …

Artificial intelligence for science in quantum, atomistic, and continuum systems

X Zhang, L Wang, J Helwig, Y Luo, C Fu, Y Xie… - arXiv preprint arXiv …, 2023 - arxiv.org
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural
sciences. Today, AI has started to advance natural sciences by improving, accelerating, and …

A latent diffusion model for protein structure generation

C Fu, K Yan, L Wang, WY Au… - Learning on Graphs …, 2024 - proceedings.mlr.press
Proteins are complex biomolecules that perform a variety of crucial functions within living
organisms. Designing and generating novel proteins can pave the way for many future …

Complete and efficient graph transformers for crystal material property prediction

K Yan, C Fu, X Qian, X Qian, S Ji - arXiv preprint arXiv:2403.11857, 2024 - arxiv.org
Crystal structures are characterized by atomic bases within a primitive unit cell that repeats
along a regular lattice throughout 3D space. The periodic and infinite nature of crystals …

Semi-Supervised Learning for High-Fidelity Fluid Flow Reconstruction

C Fu, J Helwig, S Ji - Learning on Graphs Conference, 2024 - proceedings.mlr.press
Physical simulations of fluids are crucial for understanding fluid dynamics across many
applications, such as weather prediction and engineering design. While high-resolution …

Paths towards time evolution with larger neural-network quantum states

W Zhang, B Xing, X Xu, D Poletti - arXiv preprint arXiv:2406.03381, 2024 - arxiv.org
In recent years, the neural-network quantum states method has been investigated to study
the ground state and the time evolution of many-body quantum systems. Here we expand on …

A Score-Based Model for Learning Neural Wavefunctions

X Zhang, S Xu, S Ji - arXiv preprint arXiv:2305.16540, 2023 - arxiv.org
Quantum Monte Carlo coupled with neural network wavefunctions has shown success in
computing ground states of quantum many-body systems. Existing optimization approaches …

Variational methods for solving high dimensional quantum systems

D Li - arXiv preprint arXiv:2404.11490, 2024 - arxiv.org
Variational methods are highly valuable computational tools for solving high-dimensional
quantum systems. In this paper, we explore the effectiveness of three variational methods …

Applications of Machine Learning Techniques to the Quantum Many-Body Problem

JR Moreno - 2023 - search.proquest.com
In recent years, the remarkable progress in machine learning has revolutionized various
fields, including natural sciences, and in particular the physical sciences. One area where …