Umut Özyurt
As an undergraduate researcher, I focus on applying and investigating deep learning techniques to address challenges in computer vision, particularly in generative models, object recognition, and efficient AI systems.
Education
Academic background and qualifications in computer science
Middle East Technical University (METU / ODTÜ)
B.Sc. in Computer Science (Senior Year)
09/2020 - 06/2026 (Expected) | Ankara, Turkey
CGPA: 3.88 / 4.00
Leadership
Technical Lead, METU Artificial Intelligence Society — Led technical workshops, organized events, and guided student projects in computer vision and machine learning.
Relevant Coursework (all completed with 4.0/4.0)
Honors & Awards
Recognitions of academic and research excellence
INSAIT SURF 2025
Selected for prestigious 3-month Summer Undergraduate Research Fellowship at INSAIT, with world-renowned ETH Zürich/EPFL faculty.
4000+ applicants from 150+ countries
UIUC Regh Lab Research Position
Offered summer research position to work with Ozgur Kara at the University of Illinois Urbana-Champaign. Declined due to INSAIT SURF commitment.
ICVSS 2025 Acceptance
Accepted to the prestigious 19th International Computer Vision Summer School (34% acceptance rate, primarily Master/PhD applicants). Declined due to INSAIT commitment.
Erasmus+ Traineeship Grant
Awarded funding support for research position at the University of Cambridge.
Top Project Recognition
Acknowledged for the most complex and successful project in Deep Generative Models graduate course.
High Honor Student
Recognized for 7 consecutive semesters of academic excellence.
METU Development Foundation Scholarship
Awarded for ranking in the Top 1000 among over 2.5 million applicants.
Selected Publications
Research contributions in computer vision and deep learning
Meta-LoRA: Meta-Learning LoRA Components for Domain-Aware ID Personalization
A novel approach using meta-learning for Low-Rank Adaptation (LoRA) components in diffusion models, enhancing identity preservation in text-to-image generation.
GRACE: Generating Socially Appropriate Robot Actions Leveraging LLMs and Human Explanations
A framework generating contextually appropriate robot behaviors by combining large language models with human social explanations for improved human-robot interaction.
Enhanced Thermal Human Detection with Fast Filtering for UAV Images
An approach optimizing thermal human detection on UAV platforms using efficient filtering techniques for real-time performance on edge devices.
Peer Review & Academic Service
Experience & Skills
Research and engineering experience in computer vision and deep learning
Research Experience
METU ImageLab
Computer Vision & Deep Learning Researcher (Remote)
09/2024 - Present
Advisor: Assoc. Prof. R. Gökberk Cinbiş.
Conducting research on state-of-the-art deep learning models for computer vision tasks, including generative models and diffusion techniques for personalized image generation, aiming for high-impact publications.
University of Cambridge (AFAR Lab)
Visiting Researcher / Computer Vision Engineer
07/2024 - 09/2024
Advisor: Prof. Hatice Güneş.
Contributed significantly to research on uncertainty prediction in computer vision systems. Involved in all project phases: experimental design, implementation, analysis, and manuscript preparation (second author on ICRA 2025 submission).
METU Intelligent Systems Lab
Undergraduate Researcher / Candidate Engineer
07/2023 - 07/2024
Advisor: Assoc. Prof. Seyda Ertekin.
Researched, developed, and evaluated computer vision methods for thermal human detection using UAV imagery. Focused on real-time processing via edge computing (NVIDIA Jetson). Contributed to IISEC 2023 publication as the first author.
Professional Experience
Syntonym
Computer Vision & Generative AI Researcher (Remote)
09/2024 - Present
Researching deep learning models, particularly diffusion models, for high-fidelity face anonymization. Integrating techniques like ControlNet for fine-tuning and exploring text-to-image personalization (SD1.5, SDXL, FLUX).
Infodif
Computer Vision Engineer / Researcher
01/2024 - 07/2024
Developed and optimized a face recognition pipeline for the Turkish National Police using computer vision techniques, multi-attribute recognition, and custom deep learning architectures.
AsisGuard
Candidate Computer Vision Engineer / Researcher
03/2023 - 12/2023
Led computer vision projects from inception, implementing solutions including thermal imaging analysis and object detection/tracking, optimized for edge devices (NVIDIA Jetson, custom AI accelerators). Guided interns on integration tasks.
Technical Expertise
Research Skills
Frameworks & Libraries
Programming & Tools
Computer Vision & Deep Learning
Exploring visual understanding and generation through research
My research focuses on advancing computer vision by investigating and applying innovative deep learning methodologies. I explore diverse domains such as object detection, recognition, tracking, and the analysis of visual data like thermal imagery. A key research interest lies in generative models, especially diffusion techniques, for tasks including controllable image/video synthesis. My goal is to contribute to the development of robust, efficient, and interpretable AI systems through rigorous research.
Core Deep Learning Research
Researching and refining deep neural network architectures (CNNs, Transformers, etc.) for fundamental computer vision tasks and exploring novel optimization techniques.
Generative Vision Models Research
Investigating generative models (GANs, VAEs, Diffusion) for realistic data synthesis, image editing, personalization, and exploring challenges in video generation.
Visual Recognition & Analysis Research
Researching systems for object detection, tracking, face recognition, and semantic understanding in images/videos, including specialized domains like thermal vision.
Advanced Style Transfer Implementation
Re-implemented the model and training pipeline of the CVPR 2023 paper "Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer," creatively resolving critical ambiguities. Acknowledged as the most complex and successful work of the term among graduate submissions.
View on GitHubGet In Touch
Open to research collaborations in computer vision and deep learning
Location
Ankara, Turkey