09:00 AM - 9:15 AM      Welcome and Introduction 

9:15 AM - 10:00 AM      Keynote: Filippo Menczer, Indiana University 

      Title: AI and Social Media Manipulation: The Good, the Bad and the Ugly

10:05 AM - 10:25 AM    Spotlight Talks  (2 talks, 10 min each)

• Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs - Best paper award 🎉🎉🎉

• Inverse Prompt Engineering for Safety in Large Language Models- Best Paper Runner-Up 🎉🎉

10:30 AM - 11:00 AM    Break

11:00 AM - 11:30 AM    Invited Talk: Frank Rudzicz, Dalhousie University

      Title:  Quis custodiet ipsos custodes?

11:35 AM - 11:55 AM    Spotlight Talks  (2 talks, 10 min each)

• Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models

• Improving Activation Steering in Language Models with Mean-Centring

12:00 AM - 12:30 PM   Invited Talk: Kun Zhang, Carnegie Mellon University. Mohamed bin Zayed University of Artificial Intelligence

    Topic: Causal Representation Learning: Discovery of the Hidden World

12:30 PM - 2:00 PM     Lunch and Poster Session 

02:00 PM - 3:00 PM     Panel Discussion "Bridging the Gap: Responsible Language Model Deployment in Industry and Academia"

Peter Lewis (Moderator), Ontario Tech University

Antoaneta Vladimirova, Roche

Donny Cheung, Google

Emre Kiciman, Microsoft Research

Eric Jiawei He, Borealis AI

Jillian Tang, Michigan State University 

03:00 PM - 3:30 PM      Invited Talk: Muhammad Abdul-Mageed, The University of British Columbia, Mohamed bin Zayed University of Artificial Intelligence

                                          Title: Inclusive Language Models

03:30 PM - 4:00 PM      Break

04:00 PM -  4:30 PM     Invited Talk:  Balaraman Ravindran, Professor of Computer Science at IIT Madras

      Title: InSaAF: Incorporating Safety through Accuracy and Fairness | Are LLMs ready for the Indian Legal Domain?

04:35 PM - 5:05 PM      Invited Talk: Sarath Chandar, École Polytechnique de Montréal

                                      Title: Rethinking Interpretability

05:10 PM - 05:30 PM    Spotlight Talks  (2 talks, 10 min each)

• Ethos: Rectifying Language Models in Orthogonal Parameter Space

• Towards Generating Informative Textual Description for Neurons in Language Models

05:35 PM - 5:40 PM      Closing remarks  

Note: All times are Pacific Time (PT)