Welcome! I'm starting this blog to share insights from my research at Cambridge on fundamental ML architectures and optimization.

What I'll Write About

I plan to cover topics including:

  • LLM Optimization: Techniques for making language models faster and more efficient
  • Research Insights: Learnings from my work on looped transformers and recursive architectures
  • Future of ML: Thoughts on next-generation architectures that will power future ML systems
  • Technical Deep Dives: Implementation details and experiments

Why This Blog?

I believe in sharing knowledge openly. Many of the challenges I encounter in my research are common across the field, and documenting solutions can help others facing similar problems.

Stay Connected

I'll aim to post regularly about interesting findings, paper reviews, and implementation notes. If you're working on similar problems or have questions, feel free to reach out!