Research talk

Alfred: Prompted Weak Supervision

June 28, 2024

12:00 PM - 1:00 PM PT

Register now

By submitting this form, I agree to the Terms of Use and acknowledge that my information will be used in accordance with the Privacy Policy.

During this research talk, you’ll see how researchers are pushing the boundaries of what’s possible with weak supervision.

PhD Candidate Peilin Yu from Brown University will discuss how Alfred enables users to encode their subject matter expertise via natural language prompts for language and vision-language models.

The talk will address:

  • How weak supervision scales labeling efforts.
  • How foundation models enable more user-friendly labeling.
  • How Alfred supercharges the foundation model/labeling function interface.

Speakers

Image

Peilin Yu

PhD Candidate
Brown University

Peilin Yu is a Ph.D. candidate in the Computer Science Department at Brown University, where he is advised by Professor Stephen H. Bach. He focuses on innovative methods for addressing weak supervision challenges and harnessing foundation models to improve weak supervision practices. His work has been presented at conferences such as ICLR, ACL, AISTATS, and IEEE Big Data.