🧑🔬 Zeqiu Wu — papers of 2024 — 1 paper, the most cited first1 paper · all years of Zeqiu WuUnpacking DPO and PPO: Disentangling Best Practices for Learning from Preference FeedbackConference on Neural Information Processing Systems (NeurIPS)Hamish Ivison, Yizhong Wang, Jiacheng Liu, et al.2024 · 50 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/zeqiu-wu/year/2024/