Vision Transformer - LLM Architecture
Vision Transformer Architecture。
I am Junhong Liu, working as a Research Assistant at Harbin Institute of Technology, Shenzhen (in 2024), and my researches focus on Embodied Artificial Intelligence and Multimodal Large Language Models.
On this blog, you will find posts about whatever I happen to be interested in or working on. This homepage is written in English, you can find the Chinese content (such as poetries and digests) by switching the web’s language to “中文(简体)”.
My Email: JXL1608@alumni.bham.ac.uk
Vision Transformer Architecture。
Principle of Dropout
Robotics Basics, focus on motion control for robotic arms