Profiles2024-2026
Shahaf Bassan
Hebrew University of Jerusalem
9Papers
1Last author
7Unique co-authors
7First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers9
- Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable GuaranteesAuthor 3 of 3ICLR 2026 · 10 citations
- Provably Explaining Neural Additive ModelsAuthor 1 of 7ICLR 2026 · 3 citations
- Unifying Formal Explanations: A Complexity-Theoretic PerspectiveAuthor 1 of 3ICLR 2026 · 3 citations
- SHAP Meets Tensor Networks: Provably Tractable Explanations with ParallelismAuthor 2 of 3NeurIPS 2025 · 9 citations
- Additive Models Explained: A Computational Complexity ApproachAuthor 1 of 3NeurIPS 2025 · 4 citations
- Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient ReasonsAuthor 1 of 3ICLR 2025
- Explaining, Fast and Slow: Abstraction and Refinement of Provable ExplanationsAuthor 1 of 5ICML 2025
- What makes an Ensemble (Un) Interpretable?Author 1 of 4ICML 2025
- Local vs. Global Interpretability: A Computational Complexity PerspectiveAuthor 1 of 3ICML 2024 · 28 citations
