Nicholas Gao

Nicholas Gao is a researcher at the Technical University of Munich (TUM) within the Department of Computer Science's Data Analytics and Machine Learning group (I26), working under Prof. Stephan Günnemann. His research bridges machine learning and quantum chemistry, specializing in graph neural networks for molecular simulations and ab-initio quantum computations.

His academic background includes:

• M.Sc. in Computer Science from TUM (2017-2020), thesis: Fast and Flexible Temporal Point Processes using Triangular Maps (top 10%, high distinction)
• B.Sc. in Computer Science from Technical University of Brunswick (2014-2017), thesis: Visualizing the IoT with Mixed Reality (top 10%)

Gao's research centers on graph-based machine learning for quantum chemistry, developing novel approaches to solve many-electron Schrödinger equations and model potential energy surfaces. His work integrates graph neural networks with neural wave functions to enable efficient ab-initio simulations, addressing fundamental challenges in computational chemistry through deep learning innovations.

His 2020-2024 publications reveal a clear trajectory toward solving quantum chemistry problems using geometric deep learning, with increasing focus on many-body physics and electronic structure theory. Key contributions include neural Pfaffians for Schrödinger equations (NeurIPS 2024 oral) and sampling-free potential energy surface networks (ICLR 2023), demonstrating consistent innovation at the ML-chemistry intersection.

Scientific recognition includes:

• Deutschlandstipendium from TUM (2019)
• Deutschlandstipendium from TU Brunswick (2016)

Gao currently focuses on research without listed advisees or grants. As a core member of TUM's I26 research group, he contributes to projects in robust machine learning, graph analytics, and efficient ML systems for scientific computing, maintaining active collaboration within the group's quantum chemistry and molecular modeling initiatives.