I implement concise, reproducible code and notebooks that accompany ML experiments. The emphasis is on clear baselines, reproducibility, and compact example scripts you can run locally.

Research Interests

  • Graph Representation Learning (GNN Architectures, Expressivity)
  • Over-Squashing And Over-Smoothing In Graph Neural Networks
  • Continual Deep Learning
  • Continual Reinforcement Learning
  • World Models And Model-Based Approaches
  • Model-Free Reinforcement Learning And Sample Efficiency

Research work — coming soon

I'm preparing research code, notes, and experiments. Check the research page for updates and drafts.