Skip to content
Alireza Mirrokni

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.

My interests span machine learning foundations and reliability, including statistical learning, optimization, interpretability, and multimodal reasoning. I interned at EPFL’s Machine Learning and Optimization Laboratory (MLO) with Prof. Martin Jaggi and at ISTA with Prof. Marco Mondelli. Earlier, I worked with Prof. Hossein Esfandiari and Prof. MohammadHossein Bateni. See my CV for more on my research experience.

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

conference International Conference on Machine Learning (ICML) 2026

Causal Attribution via Activation Patching

Amirmohammad Izadi*, Mohammadali Banayeeanzade*, Alireza Mirrokni*, Hosein Hasani*, Mobin Bagherian, Faridoun Mehri, Mahdieh Soleymani Baghshah

* Equal contribution.

conference Advances in Neural Information Processing Systems (NeurIPS) 2026

Budget Allocation for Unknown Value Functions in a Lipschitz Space

Mohammad Hossein Bateni, Hossein Esfandiari, Samira Hossein Ghorban, Alireza Mirrokni, Radin Shahdaei

α Authors listed alphabetically.

conference ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2027

Latest News

November 14, 2026

● 🎉 Paper accepted to KDD 2027

Our paper “Budget Allocation for Unknown Value Functions in a Lipschitz Space” has been accepted to KDD 2027!

September 24, 2026

● 🎉 Paper accepted to NeurIPS 2026

Our paper “Causal Attribution via Activation Patching” (CAAP) has been accepted to NeurIPS 2026!

May 12, 2026

● 🎉 Paper accepted to ICML 2026

Our paper “Optimal Regularization for Performative Learning” has been accepted to ICML 2026!