Sirry Chen bio photo

Email

Twitter

Github

Zhihu

Bilibili

课程

image

多元统计分析
归纳总结 + 大作业:乳腺癌数据集分析

image

图像处理与分析大作业
图像生成调研 + Drag Your GAN

image

知识表示大作业
从头自动构建LLMs知识图谱

随记

image

The reason to scaling in the computation of Attention
To prevent the gradient from exploding or disappearing

image

LLMs lost in the Middle
The performances of LLMs differ when the answers are located in different places: phenomena, analyses, and suspects


Leave a Message



Web Reference