Alireza Mirrokni
Final-year Undergraduate Student, Computer Engineering
Sharif University of Technology
I am a final-year undergraduate student in Computer Engineering at Sharif University of Technology.
I am broadly interested in the foundations and reliability of machine learning systems, including statistical learning, optimization, interpretability, and multimodal reasoning. Last summer, I was a research intern at the Institute of Science and Technology Austria (ISTA), where I worked with Prof. Marco Mondelli. Before that, I had the privilege of working with Prof. Hossein Esfandiari and Prof. MohammadHossein Bateni. I was also a research intern at Qatar Computing Research Institute (QCRI) with Prof. Ehsaneddin Asgari.
Research Interests
My current research focuses on building principled and reliable machine learning systems, ranging from theoretical foundations to modern language and vision-language models. My recent work spans several areas:- Theoretical machine learning and statistics
- Optimization and resource-aware learning
- Interpretability and causal analysis of LLMs and VLMs
- Multimodal and multilingual reasoning
Selected Publications
View all →Optimal Regularization for Performative Learning
Edwige Cyffers, Alireza Mirrokni, Marco Mondelli
Causal Attribution via Activation Patching
Amirmohammad Izadi*, Mohammadali Banayeeanzade*, Alireza Mirrokni*, Hosein Hasani*, Mobin Bagherian, Faridoun Mehri, Mahdieh Soleymani Baghshah
* Equal contribution.
Eye-Q: A Multilingual Benchmark for Visual Word Puzzle Solving and Image-to-Phrase Reasoning
Ali Najar, Alireza Mirrokni, Arshia Izadyari, Sadegh Mohammadian, Amir Homayoon Sharifizade, Asal Meskin, Mobin Bagherian, Ehsaneddin Asgari
Budget Allocation for Unknown Value Functions in a Lipschitz Space
Mohammad Hossein Bateni, Hossein Esfandiari, Samira Hossein Ghorban, Alireza Mirrokni, Radin Shahdaei
Ξ± Authors listed alphabetically.
Latest News
● π Paper accepted to ICML 2026
Our paper βOptimal Regularization for Performative Learningβ has been accepted to ICML 2026!