Workshop · Atlanta

Interpretability for Discovery: Understanding and Discovering Novel Knowledge in AI Models

Name: Interpretability for Discovery: Understanding and Discovering Novel Knowledge in AI Models
Start: 2026-12-12T08:00:00-05:00
End: 2026-12-12T17:00:00-05:00
Location: C108-C109, Georgia World Congress Center

When: Sat 12 Dec 2026, 08:00–17:00 EST
Where: C108-C109, Georgia World Congress Center
Authors: Xiaoyan Bai, Yonatan Belinkov, Ekdeep S Lubana, Yaniv Nikankin, Chenhao Tan, Amirtha Varshini Anbuchezhiyan Sindhanai
Organisations: University of Chicago, Technion, Harvard University, Goodfire AI, D. E. Shaw
QRS classification: Safety, fairness and privacy, AI, people and society

Open in schedule Official page