Title: Unlocking Complex Reasoning with Generative Models
Speaker: Siva Reddy
Date: Monday, December 2nd, 2024
Time: 2:30 PM - 3:30 PM
Location: DC 1304
Abstract: Feynman famously said, "What I cannot create, I do not understand." Yet, generative models, despite their impressive ability to produce realistic text and images, often lack deep understanding and reasoning capabilities. In this talk, we'll explore how to empower generative models to tackle complex reasoning tasks in both language and vision domains. We'll delve into post-training techniques that enhance their reasoning abilities further.
Speakers Bio: Siva Reddy is an Assistant Professor in the School of Computer Science and Linguistics at McGill University, a Facebook CIFAR AI Chair, a core faculty member of Mila Quebec AI Institute, and a research scientist at ServiceNow Research. He co-leads the McGill NLP Group. Previously, he was a postdoctoral researcher at Stanford University and a Google PhD fellow at the University of Edinburgh. His research interests are in representation learning for language with a specific focus on reasoning, grounding, conversational modeling, and safety. He received the 2020 VentureBeat AI Innovation Award in NLP, and the best paper award at EMNLP 2021.