in
Tutorial: Explain AI Models: Methods and Opportunities in Explainable AI, Data-Centric AI, and Mechanistic Interpretability Tue, Dec 2, 2025 • 9:45 AM – 10:35 AM PST

Technical Deep Dive 1

Shichang (Ray) Zhang

Abstract

Post Hoc Explanation (Feature Attribution), Data-Centric Explanation (Data Attribution), Mechanistic Interpretability (Component Attribution), A Unified View of Explainability