I'm an MPhil student at The Chinese University of Hong Kong working under Prof. Farzan Farnia. Prior to that, I obtained my Bachelor degree in Computer Engineering at Sharif University of Technology.

• Machine Learning Theory
• Optimization
• Large Language Models
• Statistics
• Generative Models

PromptSplit: Revealing Prompt-Level Disagreement in Generative Models
Mehdi Lotfian, Mohammad Jalali, Farzan Farnia
arXiv:2602.04009 [cs.LG] arXiv • Code

• PromptSplit — Kernel-based framework for detecting prompt-dependent disagreements in text-to-image models and LLMs
• Artificial-Intelligence-Mini-Projects — Classical algorithms, ML, and deep learning course projects
• Machine-Learning-Small-Projects — Implementations from graduate ML coursework
• Additional repositories (NLP, IR, sentiment analysis, etc.) available in my profile

Passionate about theoretically grounded generative AI.
Last updated: March 2026