publications

Pre-prints, conference, journal, and workshop papers.

2026

  1. ICML
    Model Soups Need Only One Ingredient
    Alireza Abdollahpoorrostam, Nikolaos Dimitriadis, Hussein Hazimeh, and 1 more author
    In International Conference on Machine Learning (ICML), 2026
  2. ICLR
    A General Framework for Black-Box Attacks under Cost Asymmetry
    Mohammadreza Salmani, Alireza Abdollahpoorrostam, and Seyed-Mohsen Moosavi-Dezfooli
    In International Conference on Learning Representations (ICLR), 2026
  3. Preprint
    Brenier Meets Adversarial Training: Optimal Transport Geometry for Robust Learning
    Alireza Abdollahpoorrostam, Ehsan Sharifian, Buse Şen, and 2 more authors
    2026
    Under review

2024

  1. NeurIPS
    SuperDeepFool: A New Fast and Accurate Minimal Adversarial Attack
    Alireza Abdollahpoorrostam, Mahed Abroshan, and Seyed-Mohsen Moosavi-Dezfooli
    In Advances in Neural Information Processing Systems (NeurIPS), 2024
  2. Workshop
    In Search of the Successful Interpolation: On the Role of Sharpness in CLIP Generalization
    Alireza Abdollahpoorrostam
    In NeurIPS 2024 AdvML-Frontiers Workshop, 2024
  3. Workshop
    Unveiling CLIP Dynamics: Linear Mode Connectivity and Generalization
    Alireza Abdollahpoorrostam, Amartya Sanyal, and Seyed-Mohsen Moosavi-Dezfooli
    In ICML 2024 Foundation Models in the Wild Workshop, 2024