My research is in the fields of machine learning, statistical mechanics and neuroscience. At Imperial College London I lead a research group focused on AI interpretability and robustness.

Right now, I’m most interested in LLMs for mathematical reasoning, improved model control beyond language, crafting synthetic tasks for understanding the abilities & limits of transformers, and pushing the boundaries on the models ability to connect information in creative ways.

I also consult on AI deployment for companies, startups and investors.

Before

Blog

For reflections on machine learning visit my Substack.

Youtube

Check my YouTube channel for deepdives and tutorials.

Publications

See Google Scholar for a full overview of my research publications.

Get in touch

To ensure I read your message, include ‘Building better ML’ in the subject line.

  1. YouTube
  2. Google Scholar
  3. LinkedIn
  4. Substack

This is a jekyll based resume template made by Ankit Sultana