Y'LOG / COLLECTION

Distillation

3 篇文章 · 均含中英文版本

10.162026

研究笔记11 min read

Train coordination and answering from outcomes, while a task-trained teacher guides the search tokens the student actually generates.

10.092025

研究笔记15 min read

Distill the capability, then use reinforcement learning to remove unnecessary thinking.

06.202025

工程实践24 min read

从 DeepSeek-R1 蒸馏到推理路径压缩，介绍 long2short DPO、质量与长度双偏好 DP-DPO 及泛化性优化实验。