Pietro Barbiero

Publications

• Foundations of Interpretable Deep Learning

  • • Pietro Barbiero
    • Mateo Espinosa Zarlenga
  • 2026
  • AAAI 2026

  Tutorial

• Scalable Evaluation and Neural Models for Compositional Generalization

  • • Giacomo Camposampiero
    • Pietro Barbiero
    • et al.
  • 2025
  • NeurIPS 2025

  Conference paper

• Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts

  • • Andrea Pugnana
    • Riccardo Massidda
    • et al.
  • 2025
  • NeurIPS 2025

  Conference paper

• Causally Reliable Concept Bottleneck Models

  • • Giovanni De Felice
    • Arianna Casanova Flores
    • et al.
  • 2025
  • NeurIPS 2025

  Conference paper

• Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shifts

  • • Mateo Espinosa Zarlenga
    • Gabriele Dominici
    • et al.
  • 2025
  • ICML 2025

  Conference paper

• Concept-based Interpretable Deep Learning

  • • Mateo Espinosa Zarlenga
    • Pietro Barbiero
  • 2025
  • AAAI 2025

  Tutorial