Events
CDS Seminar Series: Lifelong Concept Learning
Speaker: Mengye Ren
Location: 60 Fifth Avenue, Room 150
Date: Friday, February 13, 2026
Today’s AI models primarily acquire knowledge through offline, iid learning. While there are some in-context learning capabilities for online adaptation, it is still crucial to let them acquire and consolidate new concepts at deployment. In this talk, I will introduce ways to enable lifelong concept learning for machines, including learning embeddings for new visual concepts and semantic concepts, and identify concepts via unsupervised in-context clustering. Lastly, I will also introduce an unsupervised event segmentation algorithm that can support continual visual representation learning by clustering event concepts in a lifelong video.
Bio: Mengye Ren is an assistant professor of computer science and data science at New York University (NYU). He runs the Agentic Learning AI Lab. Before joining NYU, he was a visiting faculty researcher at Google Brain Toronto working with Prof. Geoffrey Hinton. From 2017 to 2021, he was a senior research scientist at Uber Advanced Technologies Group (ATG) and Waabi, working on self-driving vehicles. He received Ph.D. in Computer Science from the University of Toronto, advised by Prof. Richard Zemel and Prof. Raquel Urtasun. His research focuses on making machine learning more natural and human-like, in order for AIs to continually learn, adapt, and reason in naturalistic environments.