This is our tentative program. More details coming soon.
Tutorial
- 09h00-09h10: Welcome
- 09h10-10h30: Tutorial on Mechanistic Interpretability – Part I
- 10h30-11h00: Coffee Break
- 11h00-12h40: Tutorial on Mechanistic Interpretability – Part II
- 12h40-12h55: Discussion and Concluding Remarks.
- 12h00-14h00: Lunch Break
Workshop
- 14h00-15h00: Keynote Talk
- 15h00-15h15 (Paper presentation): Concepts Worth Having: Refining VLM-Guided Concept Bottleneck Models with Minimal Annotations
- 15h15-15h30 (Paper presentation): COCOLogic-V2: Identifying Logical Inconsistencies via Truly Hard-Negatives
- 15h30-15h45 (Paper presentation): Evaluating Meta-Feature Fidelity: Detecting Information Leakage in Interpretable Latent Spaces
- 15h45-16h00 (Paper presentation): How smoothing the affinity matrix affects neighborhood preservation in t-SNE
- 16h00-16h30: Coffee Break
- 16h30-16h45 (Paper presentation): How smoothing the affinity matrix affects neighborhood preservation in t-SNE
- 16h45-17h00 (Paper presentation): Hallucination Neurons and Where to Find Them: An Investigation into the existence of Hallucination Neurons
- 17h00-17h15 (Paper presentation): When Models Disagree: Contrastive Explainability for Clinical Mortality Prediction
- 17h15-18h00: Poster Session
