🔒 Trustworthy FMs Workshop

Foundation models are revolutionizing the way we interact with AI—powering everything from search engines to scientific discovery. But as their reach expands, so do the risks. Can we truly trust these systems—before putting them to use? 🤔

From AlexNet to LLaVA 🧠, the pace of innovation is staggering. Yet one thing remains constant: the urgent need for trustworthiness.
In the foundation model era, we ask:
🌍 What does trust mean at scale?
📜 Can classical insights still guide us?

This workshop brings together researchers, engineers, and thought leaders to confront these challenges head-on. We’ll explore how to create models that are not just powerful, but robust, fair, interpretable, and accountable.

• 🧠 Machine unlearning for foundation models
• 🧭 Bias discovery and mitigation in large-scale foundation models
• 🛡️ Adversarial attacks and defenses in foundation models
• 📏 Robustness and generalization in trustworthy foundation models
• ⚖️ Fairness-aware training and evaluation
• 🔍 Explainability and interpretability for large/black-box models
• 🧪 Ethical concerns and responsible deployment
• 📊 Benchmarks for foundation model trustworthiness
• 📉 Uncertainty quantification
• 🔐 Data provenance and security

We thank the support team for their help in organizing the workshop:

• Zeliang Zhang — University of Rochester
• Shirley Wu — Stanford University
• Chao Huang — University of Rochester
• Susan Liang — University of Rochester
• Cai Mu — DeepMind
• Kai Zhang — Ohio State University
• Chung-En Sun — UC San Diego
• Zhuo Liu — University of Rochester
• Zhiyuan Wang — UC Santa Barbara
• Jiani Liu — University of Rochester

For the full list of organizers, please visit the Organizers page.