Alireza Abdollahpoorrostam

I am a graduate researcher at EPFL, working at the intersection of the Chair of Risk Analytics and Optimization (RAO) with Prof. Daniel Kuhn and the Signal Processing Laboratory (LTS4) with Prof. Pascal Frossard.

I am drawn to the mathematical foundations of deep learning — why neural networks fail under adversarial perturbations and distribution shift, and what principled algorithms follow. My work spans adversarial robustness, generalization, and post-training methods (model merging, model editing) for foundation models, with recent focus on the optimal-transport geometry of adversarial training and distributionally robust optimization.

I aim to derive rigorous guarantees and turn them into deployable algorithms. My research has appeared at NeurIPS, ICML, and ICLR.

Before EPFL, I completed a B.Sc. in Electrical Engineering & Computer Science at Amirkabir University of Technology (Tehran Polytechnic).

Research interests

• Adversarial robustness and certified defenses
• Distributionally robust optimization & optimal transport
• Model merging, model soups, and weight-space methods
• Robust fine-tuning of vision–language foundation models (CLIP)
• Linear mode connectivity and the loss landscape

What I am working on now

• Brenier maps for adversarial training — an OT-geometric reformulation of adversarial training, toward provably robust learning algorithms (with E. Sharifian, B. Sen, M. Cuturi, D. Kuhn).
• MonoSoup — a hyperparameter-free, data-free post-hoc method that recovers Model-Soup-level OOD accuracy from a single fine-tuned checkpoint, reducing ensembling cost from $\mathcal{O}(K)$ to $\mathcal{O}(1)$ (ICML 2026).