Research
2026
- Reward-Aware Population Scaling of Evolutionary Strategies in LLM Fine-Tuning — Accepted to the HiLD Workshop at ICML 2026 (arXiv · OpenReview)
Papers I Read
- Evolution Strategies at Scale: LLM Fine-Tuning Beyond Reinforcement Learning - Qiu et al. (2025)
- ES can be used for LLM fine-tuning without RL
- A Mathematical Theory of Communication
- Prediction and Entropy of Printed English