Cover Image for Demystifying Attention Sink in LLMs and its Applications to Architecture Design
Cover Image for Demystifying Attention Sink in LLMs and its Applications to Architecture Design
27 Went

Demystifying Attention Sink in LLMs and its Applications to Architecture Design

Hosted by AER LABS & Network School
Registration
Past Event
Welcome! To join the event, please register below.
About Event

Personal website: https://guxm2021.github.io/
Google scholar: https://scholar.google.com/citations?user=BkxEuIoAAAAJ&hl

I am a final-year Ph.D. candidate from National University of Singapore, supervised by Prof. Ye Wang. I earned my B.E. degree of Electronic Engineering and B.S. degree of Finance from Tsinghua University in 2021.

I am a student researcher at Google Deepmind in London, United Kingdom, where I am hosted by Petar Veličković and Larisa Markeeva. I was lucky to be mentored by Tianyu Pang and Chao Du at Sea AI lab (SAIL), Singapore, where I also worked closely with Qian Liu and Min Lin.

My current research focus is to understand, advance and safely deploy generative models and agents. One of my long-term goals is to use test-time-scaling/agents for challenging problems, such as scientific discovery.

Location
NS Coworking Space
27 Went