AI RESEARCH
KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models
arXiv CS.AI
•
ArXi:2603.01875v2 Announce Type: replace-cross Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a homogeneous