Papers by Chuxuan Zeng
Efficient Hyperparameter Optimization for LLM Reinforcement Learning (2026.acl-long)
Copied to clipboard
| Challenge: | Existing hyperparameter optimization methods are inefficient in reinforcement learning due to model scale and resource-intensive training cycles. |
| Approach: | They propose a hyperparameter optimization method that adapts both model size and training budget as fidelity. |
| Outcome: | The proposed method significantly improves the computational efficiency of each trial (up to 14.9) over existing HPO methods. |