April 25, 2024

This Thursday (April 25), we are thrilled to welcome Prof. Chelsea Finn from Stanford as our final speaker for the 2023-2024 seminar series! You can sign up for 1-on-1 meetings here. If the schedule for one-on-one meetings is fully booked but you’re still interested in chatting, feel free to reach out to the meeting hosts to see if they’d be open to a joint session. 
Here are the details for the talk: 
WHEN: 10:30 AM, April 25 Thursday (PT)
WHERE: Allen 203. We will announce our Zoom link before the talk, but please join in person if possible!
TITLE: Learning from High-Level Language Supervision
ABSTRACT: The status-quo in machine learning is to provide supervision in the form of input-output pairs. While this is simple and performant, it can require extremely large amounts of supervision. Moreover, in reality, machine learning practitioners in practice need to iterate on the data that is provided to models; such iteration is often ad-hoc and it can be difficult to target model weaknesses. In this talk, I’ll discuss ideas for supervising machine learning models in an efficient and targeted manner, with natural language as the medium of supervision. These ideas will be studied on a diverse range of problems, including image classification, robotic manipulation, and language generation
BIO: Chelsea Finn is an Assistant Professor in Computer Science and Electrical Engineering at Stanford University and a co-founder of a new company, Physical Intelligence. Her research interests lie in the capability of robots and other agents to develop broadly intelligent behavior through learning and interaction. To this end, her work has pioneered end-to-end deep learning methods for vision-based robotic manipulation, meta-learning algorithms for few-shot learning, and approaches for scaling robot learning to broad datasets. Her research has been recognized by awards such as the Sloan Fellowship, the IEEE RAS Early Academic Career Award, and the ACM doctoral dissertation award, and has been covered by various media outlets including the New York Times, Wired, and Bloomberg. She received her Bachelor’s degree in Electrical Engineering and Computer Science at MIT and her PhD in Computer Science at UC Berkeley.