Unverified50% confidenceFactExact time
知识蒸馏最早由Hinton等人在2015年提出，DiffusionGemma创造性地将其用于步数压缩，教师模型用较多步数（如48步）生成，学生模型用更少步数（如12步）达到相近质量
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
Verified知识蒸馏由Hinton等人在2015年提出，核心思想是让小型学生模型模仿大型教师模型的输出分布79% similarUnverifiedKnowledge distillation, proposed by Hinton et al., has student models inherit implicit knowledge by learning from the soft probability distributions output by teacher models.72% similarUnverifiedKnowledge distillation was first proposed by Hinton, Vinyals, and Dean at Google in 2015, with the core idea of having a small student model learn from the soft labels output by a large teacher model.70% similarUnverified知识蒸馏由Hinton等人2015年提出，通过温度参数软化概率分布，使低概率类别的暗知识更显著供学生模型学习70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/807345API
curl https://kongchang.com/api/v1/knowledge/claims/807345MCP
get_claim(id=807345)