tommy chu

MSc Data Science at EPFL

Master student at EPFL interested in HPC and efficient deep learning methods (model compression, pruning, quantization) and using ML for science (drug discovery, weather prediction).

Research

  • T. Chu, A. Kovalenko. Projective Pruning by Decoupling Weights. Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2025), Research Track. Lecture Notes in Computer Science, vol 16018. Springer.
    doi.org/10.1007/978-3-032-06106-5_19
  • T. Chu. Machine Learning Techniques for Weather Events Forecasting. Bachelor's thesis, Faculty of Information Technology, Czech Technical University in Prague, 2025. Advisor: A. Kovalenko.
    hdl.handle.net/10467/124324

Experience

  • Student Researcher, Czech Technical University
    • neural network compression (pruning, sparsification, quantization).
    • spatiotemporal modeling with PINNs for extreme weather prediction.
  • Scientific Software Engineer, Merck & Co. (MSD)
    • building data infrastructure for generative models for drug discovery, multimodal molecular representations (SMILES, voxel, point-cloud, graph),
    • working on a petabyte-scale platform for virtual screening, next-generation sequencing, combinatorial chemistry.
    • accelerated protein-ligand molecular-dynamics simulations with IO competitions, on-prem HPC to cloud migration.

Education

  • EPFL, MSc Data Science
  • Czech Technical University in Prague, BSc Computer Science

    GPA 4.00/4.00

  • prg.ai Minor, Czech AI research initiative

    interdisciplinary AI program run jointly by CTU and Charles University

  • IBM Quantum Summer School

    qiskit: theory to implementation

Projects

a pile of random things i built for fun over the years, mostly to learn something or mess around. browse them all.