Self-Improving AI / Automated Research
Recursive Self-Improvement for ML Research and Engineering
Implementing and evaluating self-improvement approaches for kernel optimization and ML algorithm development.
My ongoing research at Stanford explores recursive self-improvement for ML research and engineering. I implement and empirically evaluate approaches for kernel optimization and ML algorithm development.
This work is part of my broader aim to build self-improving AI systems for automated research through algorithm design, studying how computational feedback can support continual improvement.
My Role
I work as a research assistant with Prof. Yejin Choi, Prof. Jure Leskovec, and Dr. Fang Wu. My work focuses on implementing recursive self-improvement approaches and evaluating them empirically in ML research and engineering tasks.
