I am a first second year Computer Engineering Ph.D. student at UC San Diego, where I am fortunate to be advised by Professor Farinaz Koushanfar.
I spent summer of 2025 as a research intern at Snap Inc., working with Yozen Liu with guidance from Dr. Neil Shah in the User Modelling and Personalization team on Lens ranking and retrieval. During my time I contributed to the Snap ML framework on large-scale gnn training and deployment.
Prior to joining UCSD, I spent ~3 wonderful years at Volkswagen and Audi of America as an AI engineer where I had the opportunity to work on AI Trajectory Planner, Vision, and LLMs in autonomous driving under the supervision of Dr. Kacem Abida and Dr. Alireza Shamsoshoara. I also received my B.Sc. degree in CS with highest honors from University of Tehran.
My research interests lie in the intersection of machine learning, security, and privacy, as well as robotics and natural language processing.
LLM Ghostbusters: Surgical Hallucination Suppression via Adaptive Unlearning
Pedram Aghazadeh †, Joseph Spracklen†, Farinaz Koushanfar, Murtuza Jadliwala
Under review
Beyond Perplexity: A Lightweight Benchmark for Knowledge Retention in Supervised Fine-Tuning
Pedram Aghazadeh †, Soheil Zibakhsh Shabgahi†, Farinaz Koushanfar
Under review
ForTIFAI: Fending Off Recursive Training Induced Failure for AI Model Collapse
Pedram Aghazadeh †, Soheil Zibakhsh Shabgahi†, Azalia Mirhoseini, Farinaz Koushanfar
Nature Parnter Journal of Artificial Intelligence
SwapTransformer: Highway overtaking tactical planner model via imitation learning on OSHA dataset
Pedram Aghazadeh †, Alireza Shamsoshoara†, Safin B Salih†
IEEE Access
OSHA dataset
Pedram Aghazadeh †, Alireza Shamsoshoara†, Safin B Salih†
IEEE DataPort
UCSD ECE department Fellowship, 2024
Direct acceptance via exceptional talents to M.Sc. program at University of Tehran, 2022
Full Resume in PDF.
This website design is based on the template from Martin Saveski.