This is my safe haven to share my notes about AI Research. Some of the domains I’ve explored here are:
I hope you enjoy reading this!
Some features:
- Check out my notes from the recent Large Model Safety Workshop 2025, and other Talks.
- Read about my previous research on WalledEval, a LLM Safety Evaluation Toolkit.
- Check out my summary of LASTS, a Time Series Interpretability method.