P. Frossard

Latest

• Task arithmetic in the tangent space: Improved editing of pre-trained models
• Catastrophic overfitting can be induced with discriminative non-robust features
• PRIME: A few primitives can boost robustness to common corruptions
• A structured dictionary perspective on implicit neural representations
• What can linearized neural networks actually say about generalization?
• A neural anisotropic view of underspecification in deep learning
• Neural Anisotropy Directions
• Hold me tight! Influence of discriminative features on deep network boundaries
• Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
• Redundant features can hurt robustness to distribution shift
• On the Choice of Graph Neural Network Architectures
• Forward-Backward Splitting for Optimal Transport based Problems