Thomas X. Wang
Thomas X. Wang

PhD Student in Deep Learning

About Me

I am a third-year PhD student in Artificial Intelligence at Sorbonne Université, working with the MLIA team within the ISIR (Robotics) laboratory. My research lies at the intersection of deep learning and dynamical systems, where I leverage AI models to solve complex parametric PDEs, under the supervision of Pr. Patrick Gallinari and Assoc. Prof. Nicolas Baskiotis. My ultimate goal is to develop AI tools that not only advance theoretical understanding but also have a tangible impact on solving real-world scientific and engineering problems.

Feel free to reach out to me for collaborations or opportunities in AI and machine learning!

Interests
  • Artificial Intelligence
  • Dynamical Systems
  • Computer Vision
Education
  • PhD in Artificial Intelligence, 2021-now

    Sorbonne Université

  • MSc in Artificial Intelligence, 2021

    Sorbonne Université

  • MSc in Industrial Engineering, 2018

    Ecole Centrale Paris (now CentraleSupelec)

Recent Publications
(2024). Zebra: In-Context and Generative Pretraining for Solving Parametric PDEs. arXiv.org.
(2024). Weight Conditioning for Smooth Optimization of Neural Networks. In ECCV 2024.
(2024). AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields. In NeurIPS 2024.
(2024). AutoBasisEncoder: Pre-trained Neural Field Basis via Autoencoding for Operator Learning. In ICLR 2024 Workshop on AI4DifferentialEquations In Science.
(2023). Operator Learning with Neural Fields: Tackling PDEs on General Geometries. In NeurIPS 2023.