Zhi-Quan Luo

Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation

Scalable Exploration via Ensemble++

Adam-mini: Use Fewer Learning Rates To Gain More

Preserving Diversity in Supervised Fine-Tuning of Large Language Models

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems

Scalable Exploration via Ensemble++