General Event

CAIDA/TrustML 2025 ICML Visits

We are excited to announce that CAIDA and the Trustworthiness of Machine-Learning-Based Systems (TrustML) Research Cluster are organizing a UBC-hosted event collocated with ICML 2025. The event will take place on July 15 and will be attended by several international speakers, providing excellent opportunities for networking with the research community in this field.

Please Register Here

Please Register by 4pm on July 9th so that we can estimate food quantities.

Tentative Program 

*Pacific Standard Time (US & Canada)

9:30
Qi Zhu, Northwestern University
Building Safe Embodied AI Systems

10:15
Han Yu, Nanyang Technology University
Challenges and Opportunities for Federated Learning in the Age of Foundation Models

11:00
Coffee Break and Poster Session

11:30
Bo Han, Hong Kong Baptist University 
Exploring Trustworthy Foundation Models: Benchmarking, Finetuning, and Reasoning

12:15
Moontae Lee, University of Illinois Chicago
Learning to Unlearn: Robust and Efficient Machine Unlearning for Large Foundation Models

1:00  
Lunch and Poster Session

2:00
Meng Wang, Rensselaer Polytechnic Institute
Efficient Inference of Mixture of Experts (MoE)-based Large Models with Theoretical Guarantees

2:45
Lin Yang, UCLA
Reinforcement Learning With Constraints: From Theory to Reasoning in LLM

3:30
Coffee Break and Poster Session

4:00
Hao Zhu, UT Austin
TrustML in Power Grids: Security, Robustness, and Statistical Risks

4:45
Hogun Park, Sungkyunkwan University
Providing Explanations for Unsupervised Graph Learning Models

This program is subject to change

If you are interested in presenting a poster at the event, please complete this form.

Please Register Here