👋 Welcome!

Hi, I’m Ali! Welcome to my academic homepage.

I am a second-year Ph.D. student and University Fellow in Computer Science at Temple University, where I am fortunate to be advised by Prof. Dragut.

My current research is centered on Multimodal AI, specifically exploring how Vision-Language Models (VLMs) and Large Language Models (LLMs) reason over structured scientific diagrams. I actively design evaluation benchmarks, analyze failure modes, and develop methods to improve model robustness on Entity-Relationship (ER) diagrams.

Before joining Temple, I earned my Bachelor of Science in Computer Engineering from the Amirkabir University of Technology (AUT) in 2024. My earlier research includes work published at ICWR 2023 on transformer-based Persian language recognition.

🚀 Internship Search: I am actively seeking a Summer or Fall 2026 research internship where I can apply my multimodal Machine Learning expertise to build and improve real-world systems.

🔬 Research Interests

• 🖼️ Multimodal AI & Vision-Language Models (VLMs)
• 🗣️ Natural Language Processing (NLP) & LLMs
• 📊 Reasoning over Structured Scientific Diagrams
• 🔍 Information Retrieval & Named Entity Recognition (NER)
• 🧠 Machine Learning & Deep Learning

📢 Updates & News

• [Feb 2026] 🏛️ I had the wonderful opportunity to present my paper (currently under review), “ERUnderstand,” to the Database Group at the University of Pennsylvania (UPenn)!
• [Jan 2026] 👨‍🏫 I started a new role as a Teaching Assistant for the Projects in Data Science course at Temple University.