Trustworthy AI Reading Group

Trustworthy AI Reading Group 

Welcome to the Trustworthy AI Reading Group! This reading group is dedicated to exploring critical topics in AI, including fairness, security, explainability, and their broader applications. We aim to create an inclusive environment that fosters lively discussions and encourages participation from undergraduate, master’s, and PhD students alike.

Organizers:

Dr. Sharon Levy, Department of Computer Science, Rutgers University

Dr. Ruixiang (Ryan) Tang, Department of Computer Science, Rutgers University

Meeting Details:

Each session will include the presentation and discussion of one or two research papers. We look forward to your participation!

If you're interested in AI research or curious about the ethical and technical challenges of Trustworthy AI, we would love to have you join us. We highly encourage students to present their own work, ideas, or interesting papers. Please feel free to edit the CSV file [link] to select a time and paper you'd like to present and send an email to the organizers (s.levy@rutgers.edu, ruixiang.tang@rutgers.edu).

Feel free to share this with anyone who might be interested!

Schedule

Date

Presenter

Title

Video (if available)

Oct 22, 2024

Understanding, Integrating, and Deploying Responsible AI: A Tale About Privacy

Oct 29, 2024

Canceled

Canceled

Nov 12, 2024

Canceled

EMNLP Conference

Nov 19, 2024

Prof. Sharon Levy

Discovering Implicit Social Biases in Large Language Models

Nov 26, 2024

Canceled

Thanksgiving Recess

Dec 3, 2024

SLMRec: Empowering Small Language Models for Sequential Recommendation