Atlanta, Georgia, United States
I’m a PhD student in Machine Learning at Georgia Tech (ISyE) and MSc in Computer Science (ML specialization), working at the intersection of generative modeling, computer vision, and robust statistical learning. My research focuses on developing robust diffusion models and generative frameworks for unsupervised anomaly detection and segmentation, where traditional assumptions about “clean” data break down. I design methods that make generative models resilient to real-world noise and contamination — enabling reliable performance in manufacturing and scientific imaging domains. My work has been accepted to ICCV VISION 2025 and ICMLA 2025, and applied in collaborations with Ford Motor Company (battery analytics), Politecnico di Milano (additive manufacturing), and the U.S. Department of Energy (PV panel smoke/fire detection). Previously, I was a Research Intern at Georgia Tech Research Institute (GTRI), where I trained 3D diffusion and vision-transformer policies for robotic manipulation and developed depth-guided diffusion augmentation pipelines for synthetic data generation. 💡 Research Interests: Generative AI · Diffusion Models · Computer Vision · Anomaly Detection · Robust Deep Learning · High-Dimensional Data Analytics 🎯 Actively seeking Research Internship and Full-Time opportunities in Summer/Fall 2026 — particularly in Generative AI, Diffusion Models, and Applied Machine Learning Research. 📬 Feel free to connect or reach out if you’re working on advancing the next generation of robust, interpretable generative models!
I am a GTA for ISyE 3133 (Optimization) which is an undergraduate course. I hold weekly tutoring sessions for students.
Reduced Sim2real Gap In Robot Learning: Improve generalization of Machine Learning models trained on synthetic datasets in real world using Generative AI.
Transportation Planning Instructor: Dr. Erfan Hassannayebi Theory of Probabilities and Its Application Instructor: Prof. S.T.A. Niaki Engineering Statistics Instructor: Dr. Majid Khedmati Motion and Time Study Instructor: Dr. Mehdi Shafiei