Trainee Spotlight: Kexuan Xin
Kexuan Xin is a postdoc in the Computer Science department at UIUC. She is an expert in knowledge graphs (specifically entity alignments!). In addition to her role in MMLI, she is excited to be working on a project with CABBI right now. [Click above to read more!]
Faculty Spotlight: Richard Zanibbi
Richard Zanibbi is a professor at Rochester Institute of Technology, coming to RIT and MMLI from a postdoc fellow position at the Centre for Pattern Recognition and Machine Intelligence at Concordia University in Montreal, Canada. Richard directs the Document and Pattern Recognition Lab, which helps MMLI identify new methods to extract molecules from PDFs.[Click above to read more!]
MMLI Trainee Spotlight: Kexuan Xin!
What is your background?
My PhD research background is in knowledge graphs, especially entity alignment. I currently focus on a CABBI project and I’m very excited to be working on it right now.
What drew you to MMLI?
I’m interested in make LLM (language learning models) work for the science domain, so I chose MMLI.
What has been your favorite part of being a part of MMLI?
My favorite part is that I can see different people from different research background contribute together for the same big project.
How do you like to spend your free time? (or what would you do for fun if you had more free time!)
I often relax at home at my free time, like watching movies.
Fun fact (or extremely average fact) about yourself you would like to share
Recently, to lose weight and keep fit, I focus on making healthy but also delicious food at home.
MMLI Faculty Spotlight: Let’s meet Richard Zanibbi
What is your background/what did you do before your current role?
I was an NSERC postdoctoral fellow at the Centre for Pattern Recognition and Machine Intelligence at Concordia University in Montreal, Canada.
What is your current position/short description of what you are working on right now with MMLI.
I am a professor of computer science at RIT, where I direct the Document and Pattern Recognition Lab. For MMLI we are working on new methods for extracting molecules from PDF files using both PDF drawing instructions and images. Our approach is designed to be relatively general, and applicable to other diagram and notation types (e.g., math, flowcharts, etc.).
What drew you to MMLI (or your lab)?
I have been working in document recognition and information retrieval for years. The extraction and information pipelines needed for mining the literature for MMLI fit well within those areas, and I was interested in exploring a new domain to broaden my understanding of these tasks, and to collaborate with other researchers in computing and chemistry interested in using our extraction models for scientific applications.
How do you like to spend your free time?
Trying new foods with family and friends, choral singing, and biking.
Fun fact (or extremely average fact) about yourself you would like to share.
My first undergraduate degree was a Bachelor of Music from Queen’s University, Canada.