Alireza Dehghanpour Farashah

PhD Student in Computer Science

McGill University and Mila, Quebec AI Institute

Montréal, Canada

I am Alireza, a PhD student in Computer Science at McGill University and Mila, Quebec AI Institute.

My research lies at the intersection of machine unlearning and concept erasure, with a particular focus on large-scale vision-language and text-to-image models. I study how undesired concepts, such as sensitive, biased, or copyrighted information, can be selectively removed from trained models while preserving their overall utility.

My academic background includes a Bachelor’s degree in Computer Engineering from Sharif University of Technology, where I developed a strong foundation in machine learning and computer vision. Building on this background, my current work investigates robustness, reliability, fairness, and safety in modern generative models, with the goal of developing principled methods for controllable and responsible AI systems.

selected publications

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models

Zhuan Shi*, Alireza Dehghanpour Farashah*, Rik Vries, and 1 more author

In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026

* Equal contribution

arXiv Bib

@inproceedings{shi2026neighbor,
  title = {Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models},
  author = {Shi*, Zhuan and Farashah*, Alireza Dehghanpour and de Vries, Rik and Farnadi, Golnoosh},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026},
  url = {https://arxiv.org/abs/2603.25994},
  note = {* Equal contribution}
}

Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs

Alireza Dehghanpour Farashah, Aditi Khandelwal, Marylou Fauchard, and 3 more authors

In Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2026

Oral Presentation

arXiv Bib

@inproceedings{farashah2026multilingual,
  title = {Multilingual Amnesia: On the Transferability of Unlearning in Multilingual LLMs},
  author = {Farashah, Alireza Dehghanpour and Khandelwal, Aditi and Fauchard, Marylou and Shi, Zhuan and Rostamzadeh, Negar and Farnadi, Golnoosh},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (EACL)},
  year = {2026},
  url = {https://arxiv.org/abs/2601.05641},
  note = {Oral Presentation}
}