- XAI_transformers
- Neural Networks Forget to Forget: Fixing the Memory Problem With Tensor Decomposition
- Robust Classifiers Energy Based Models
- Breaking Privacy Barriers: Nonparametric Testing in Federated Learning
- Fairness in Social Influence Maximization via Optimal Transport
- Knowledge Distillation: Boosting Interpretability in Deep Learning Models
- Unraveling the Mysteries of Language Models: The Power of Edge Pruning in Finding Transformer Circuits
- Understanding Visual Feature Reliance Through the Lens of Complexity
- MaNo
- When Fairness Meets Privacy
- Get a calibrated and efficient model with tailored data augmentation.
- A Groupe Fairness
- BitFit: BIas-Term FIne-Tuning
- LoRA: Low-Rank Adaptation of Large Language Models
- Privacy Amplification: How Decentralization Enhances Data Protection
- SelfIE: When Large Language Models Explain Their Own Thoughts
- Axiomatic Explanations for Visual Search, Retrieval and Similarity Learning
- Robust or Fair
- XCM, an explainable CNN for MTS classficiation
- RobustAI_RegMixup
- Learning Fair Scoring Functions: Bipartite Ranking under ROC-based Fairness Constraints
- Label-Free Explainability
- Adversarially Reweighted Learning
- Packed Ensembles
- A Framework to Learn with Interpretation
- NTK-SAP: IMPROVING NEURAL NETWORK PRUNING BY ALIGNING TRAINING DYNAMICS
- Do Perceptually Aligned Gradients imply Robustness?
- To update or not to update? Neurons at equilibrium in deep models
- Optimal Transport Based Adversarial Patch Attacks
- Statistical Minimax Rates Under Privacy
- Measuring the Transferability of Pre-trained Models: a link with Neural Collapse Distances on Target Datasets