The chair organised a workshop on explainable AI, with three talks:
- Correlations Do Not Imply Causation: Causality as a Means to an End for Mechanistic Interpretability — Q. Bouniot
- Learning to Steer: Input-Dependent Steering for Multimodal LLMs — J. Parekh
- By Design, Not by Chance: Transparent and Auditable Deep Learning Models — Y. Choho