avatar

Keivan Rezaei

Ph.D. Student
University of Maryland
krezaei@umd.edu


Bio

I am a third-year Ph.D. student at the University of Maryland, advised by Prof. Feizi and Prof. Hajiaghayi. My research focuses on the interpretability of generative AI models from both a model perspective—localizing knowledge within models, detecting, and explaining their failure modes—and a data perspective, analyzing the impact of individual data points on a model through challenges like unlearning and data selection for language model pretraining. Furthermore, I have proposed methods for integrating ads into the output of LLMs as a strategy to monetize them effectively.

News

  • [Jan 2025] I'll be joining Google as Student Researcher for Spring 2025 to work on data selection in large language model pretraining.
  • [Jan 2025] My internship project "RESTOR: Knowledge Recovery through Machine Unlearning" is now on arXiv.
  • [Sep 2024] Our paper "Ad Auctions for LLMs via Retrieval Augmented Generation" is accepted to NeurIPS 2024.
  • [May 2024] Our paper "On Mechanistic Knowledge Localization in Text-to-Image Generative Models" is accepted to ICML 2024.
  • [March 2024] I will be joining MOSAIC at Allen Institute for AI (Ai2) as Research Intern in summer 2024!
  • [Jan 2024] Our papers "PRIME: Prioritizing Interpretability in Failure Mode Extraction" and "Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks" are accepted to ICLR 2024.

Publications

  1. arXiv
    RESTOR: Knowledge Recovery through Machine Unlearning
    Keivan Rezaei, Khyathi Chandu, Soheil Feizi, Yejin Choi, Faeze Brahman, Abhilasha Ravichander
    arXiv (preprint)
    PDF Code

  2. ICML
    On Mechanistic Knowledge Localization in Text-to-Image Generative Models
    Samyadeep Basu*, Keivan Rezaei*,Ryan Rossi, Cherry Zhao, Vlad Morariu, Varun Manjunatha, Soheil Feizi
    International Conference on Learning Representations (ICML), 2024.
    PDF Code

  3. ICLR
    PRIME: Prioritizing Interpretability in Failure Mode Extraction
    Keivan Rezaei*, Mehrdad Saberi*, Mazda Moayeri, and Soheil Feizi
    International Conference on Machine Learning (ICLR), 2024.
    PDF

  4. ICML
    Text-To-Concept (and Back) via Cross-Model Alignment
    Mazda Moayeri*, Keivan Rezaei*, Maziar Sanjabi, and Soheil Feizi
    International Conference on Machine Learning (ICML), 2023.
    PDF Code

  5. NeurIPS
    Ad Auctions for LLMs via Retrieval Augmented Generation
    α, β Mohammad Hajiaghayi, Sébastien Lahaie, Keivan Rezaei, Suho Shin
    Neural Information Processing Systems. (NeurIPS), 2024.
    PDF

  6. ICML
    Run-Off Election: Improved Provable Defense against Data Poisoning Attacks
    Keivan Rezaei*, Kiarash Banihashem*, Atoosa Chegini, and Soheil Feizi
    International Conference on Machine Learning (ICML), 2023.
    PDF Code

  7. ICLR
    Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
    Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Chegini, Wenxiao Wang, Soheil Feizi
    International Conference on Learning Representations (ICLR), 2024.
    PDF

  8. EC
    Multi-agent Delegated Search
    α, β MohammadTaghi Hajiaghayi, Keivan Rezaei and Suho Shin
    Conference on Economics and Computation (EC), 2023.
    PDF

  9. AAAI
    Regret Analysis of Repeated Delegated Choice
    α, β MohammadTaghi Hajiaghayi, Mohammad Mahdavi, Keivan Rezaei, and Suho Shin
    The Association for the Advancement of Artificial Intelligence (AAAI), 2024.
    PDF

    10. α, β denotes alphabetical order of authorship.
    * denotes equal contribution.

Services

Conference Reviewers


Powered by Jekyll and Minimal Light theme.