Samir Darouich

Samir Darouich

Visiting PhD Student

University of Stuttgart

I am a PhD student in Theoretical Chemistry and Machine Learning at the University of Stuttgart, where I also earned my Bachelor’s and Master’s degrees in Chemical Engineering. My research centers on developing machine learning approaches to elucidate chemical reactivity, with a focus on transition states and generative modeling. Prior to my doctoral studies, I worked extensively in molecular modeling with classical force fields, from their development to applying them for predicting interfacial phenomena in materials and industrial processes.

Interests
  • generative machine learning
  • chemical reactions
  • molecular dynamics
Education
  • MS in Chemical Engineering, 2023

    University of Stuttgart

  • BS in Chemical Engineering, 2021

    University of Stuttgart

Publications

  1. ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table (2026)
  2. Physics-based molecular fingerprints from spectral graph theory provide efficient geometry-aware measures of chemical similarity (2026)
  3. Robust generative transition-state models for unseen chemistry (2026)
  4. Curvature-aware flow matching for molecular structure generation (2026)