Thibaut Boissin

CRAFT: Concept Recursive Activation FacTorization for Explainability

2022 · arXiv (Cornell University)

Attribution methods, which employ heatmaps to identify the most influential regions of an image that impact model decisions, have gained widespread popularity as a type of explainability method. However, recent research has exposed the limited …

Turbo-Muon: Accelerating Orthogonality-Based Optimization with Pre-Conditioning

2025 · arXiv (Cornell University)

Orthogonality-based optimizers, such as Muon, have recently shown strong performance across large-scale training and community-driven efficiency challenges. However, these methods rely on a costly gradient orthogonalization step. Even efficient iterative approximations such as Newton-Schulz remain …

Back to the Baseline: Examining Baseline Effects on Explainability Metrics

2025 · arXiv (Cornell University)

Attribution methods are among the most prevalent techniques in Explainable Artificial Intelligence (XAI) and are usually evaluated and compared using Fidelity metrics, with Insertion and Deletion being the most popular. These metrics rely on a …