热点
"参考模型" 相关文章
Not All Preferences are What You Need for Post-Training: Selective Alignment Strategy for Preference Optimization
cs.AI updates on arXiv.org 2025-07-11T04:04:14.000000Z
Nat. Methods | 基于单细胞RNA测序的植入前小鼠和人类胚胎深度学习模型
智源社区 2024-12-03T16:52:15.000000Z
How Important is the Reference Model in Direct Preference Optimization DPO? An Empirical Study on Optimal KL-Divergence Constraints and Necessity
MarkTechPost@AI 2024-08-01T06:34:34.000000Z