Marti Hearst, Berkeley
Monday, August 21st, 2023 – 1:30-2:30pm
A First Look at LLMs Applied to Scientific Documents
Dr. Marti Hearst is a Professor and Head of School at UC Berkeley in the School of Information and the Computer Science Division. Her research encompasses user interfaces with a focus on search, information visualization with a focus on text, computational linguistics, and educational technology. She is the author of Search User Interfaces, the first academic book on that topic. She co-founded the ACM Learning@Scale conference, is a former President of the Association for Computational Linguistics, a member of the CHI Academy and the SIGIR Academy, an ACM Fellow, an ACL Fellow, and has received four Excellence in Teaching Awards from the students of UC Berkeley. She received her PhD, MS, and BA degrees in Computer Science from UC Berkeley and was a member of the research staff at Xerox PARC.
Vlad Morariu, Adobe Research
Tuesday, August 22nd, 2023 – 1:30-2:30pm
Enabling the Document Experiences of the Future
Vlad Morariu is a senior research scientist with Adobe Research and is part of the Document Intelligence Lab (DIL). His research interests include combining computer vision, natural language, machine learning, and artificial intelligence techniques to develop rich visual and linguistic models for multimodal structured content. His current focus is to develop such models to power the next generation of document consumption and authoring experiences. Vlad received the BS and MS degrees from the Pennsylvania State University, in 2005, with Professor Octavia I. Camps as his thesis advisor. He received the PhD degree from the University of Maryland, in 2010, with Professor Larry S. Davis as his advisor. After completing his doctoral studies, he continued as a postdoctoral researcher and then as a research scientist at the University of Maryland until 2018, when he joined Adobe Research. He has co-authored more than 60 peer-reviewed publications including more than 30 in top-tier conferences (ICCV, CVPR, ECCV, NeurIPS, AAAI, EMNLP, ACL, NAACL). He served as area chair for WACV 2017, 2020-2023 and he served as program committee member for many computer vision and AI conferences, including Computer Vision and Pattern Recognition, ICCV, ECCV, AAAI, and IJCAI. He is currently an associate editor of IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) and is currently serving as program chair for WACV 2024.
Seiichi Uchida, Kyushu University
Wednesday, August 23rd, 2023 – 1:30-2:30pm
What Are Letters?
We DAR researchers have been working on recognizing, understanding, and generating characters. In particular, we have dramatically improved the accuracy of recognition and generation with recent machine-learning techniques. Through those improvements, we can now detect and recognize scene texts and generate a variety of fonts. On the other hand, how much do we know about letters themselves? What is ‘A?’ How is the alphabet constructed? Why are there so many different fonts? In this talk, I would like to introduce some research results and open problems related to these questions.
Prof. Uchida received B.E. and M.E., and Dr. Eng. degrees from Kyushu University, Japan, in 1990, 1992, and 1999, respectively. He is currently Senior Vice President and Distinguished Professor at Kyushu University. He was Co-Program Chair for ICDAR 2021, DAS 2012, and 2022.