Human-AI Alignment
Date
Tuesday, 02 December 2025
Time
09:30 AM – 12:00 PM PST
Location
Exhibit Hall F, San Diego Convention Center
Tutorial Outline
🏛️
Foundations
Preferences, Values, and Morals
⚙️
Methods
Specification & Alignment Methods
🤝
Practice
Sociotechnical Evaluation and Oversight
⛰️
Challenges
AI Safety & Extreme Risks
-
I
Introduction | Hua Shen [Slides]
-
II
Human-in-the-loop AI and Value Alignment | Hua Shen [Slides]
-
III
Pluralistic and Collective Alignment | Mitchell Gordon [Slides]
-
IV
Evaluation and Oversight | Adam Kalai [Slides]
-
V
A Safety Argument for the Scientist AI | Yoshua Bengio [Slides]
-
PANEL: Alignment Challenge & Prospects | See Our Panelists Below
Panelists
Check Details & Join Us
Don't miss this in-depth tutorial on the future of AI alignment.
Learn More & Register