About Me
I am currently a Machine Learning Scientist at Amazon Prime Video, where I focus on Video-Language Foundational Models. Previously, I was a Postdoctoral Research Fellow at the Stanford AI Lab, Stanford University, working under the guidance of Dr. Stefano Ermon. My special thanks go to my advisor Dr. Ermon for his mentorship and support.
My research at Stanford focused on developing efficient convolutional networks optimized for run-time complexity, advancing unsupervised and weakly supervised learning methods to improve sample efficiency in downstream tasks, exploring generative models, and applying machine learning to computational sustainability challenges.
I earned my Ph.D. from the Chester F. Carlson Center for Imaging Science at Rochester Institute of Technology, advised by Dr. Matthew J. Hoffman.
Education
| Degree | Institution | Years | Research Focus |
|---|---|---|---|
| Ph.D. | Chester F. Carlson Center for Imaging Science, RIT | 2011–2016 | Aerial Vehicle Detection and Tracking using a Multi-modal Adaptive Sensor |
| M.S. | Electrical & Computer Engineering, University of Bridgeport | 2009–2011 | Non-speech Environmental Sound Classification with Pitch Range-based Features |
| B.S. | Electrical & Electronics Engineering, Eskisehir Osmangazi University | 2004–2009 | Autonomous Parallel Parking of Non-holonomic Vehicles |
Professional Experience
Machine Learning Scientist | Amazon | Apr 2022 – Present
Video-Language Foundational Models
Sr. Research Scientist | Samsung Research America | Nov 2020 – Apr 2022
Vision Transformer Compression • Multimodal Understanding
Postdoctoral Research Fellow | Stanford University | Jul 2018 – Oct 2020
Unsupervised & Weakly Supervised Learning • Efficient Computer Vision • Generative Models • Computational Sustainability
Computer Vision Engineer | Planet Labs | Jun 2017 – Jul 2018
Convolutional Object Detection in Low-Resolution Aerial Imagery
Computer Vision Engineer | Autel Robotics | Aug 2016 – Jun 2017
High-Speed Object Tracking on Low-End Embedded Systems
Computer Vision Algorithm Engineer Intern | Huawei R&D | Nov 2015 – May 2016
Unsupervised Semantic Role Assignment in Photo Albums
Research Interests
- 🎥 Video-Language Understanding
- 🔬 Efficient Deep Learning & Model Compression
- 🤖 Multimodal Machine Learning
- 🌱 Computational Sustainability
- 🎨 Generative Models