prof_pic.jpg

Can Koz

can dot koz at some dot ox dot ac dot uk

I am a MSc in Advanced Computer Science student at University of Oxford. I am currently being mentored by Dr. Tomas Jakab and Luke Melas-Kyriazi at Visual Geometry Group. My thesis focuses on developing animatable and deformable 3D objects using generative modeling techniques.

Previously I worked as a Large Language Model Engineer, where I worked on projects at the intersection of machine learning, air charter services. I have also worked as a Computer Vision Engineer focusing on event-based vision.

I was an undergraduate researcher at Visual Design and Engineering Lab (VDEL) in the Mechanical Engineering Department at CMU for three years. I was advised by Prof. Levent Burak Kara, Wentai Zhang and Kevin Ferguson. As an undergraduate research assistant, I solved problems in mechanical engineering using deep learning / computer vision such as flaw detection in metal additive manufacturing and generating / understanding engineering design. During my studies in the US, I worked with undergraduate CS students from UC Berkeley, Stanford and MIT on projects at the intersection of machine learning, healthcare, and finance. Click here to see my projects!

Over the past couple of years, I have also taken non-degree machine learning courses on Coursera. I have completed Deep Learning Specialization, AI for Medicine Specialization and Self-Driving Cars Specialization. I am currently learning financial machine learning and building high frequency trading bots, with a particular interest in applying reinforcement learning techniques to optimize trading strategies. When I’m not in front of a screen, I enjoy rowing, playing drums, and reading science fiction novels.

I am a proud mentor at AI for Medicine Specialization , Deep Learning Specialization and a member of the Learning on Graphs and Geometry Reading Group (LoGG).

news

Oct 30, 2023 Our paper “Multi-task Learning for Optical Coherence Tomography Angiography (OCTA) Vessel Segmentation” was accepted to Medical Imaging Meets NeurIPS 2023
Oct 15, 2023 I was a reviewer at the Temporal Graph Learning Workshop at NeurIPS 2023
Oct 1, 2023 Excited to start my MSc in Advanced Computer Science at University of Oxford.
Aug 1, 2022 Our paper “Data Augmentation of Engineering Drawings For Data-Driven Component Segmentation” was accepted to IDETC-CIE 2022.
Jul 1, 2022 Graduated from Koc University, Computer Engineering Department with Dean’s Student Award

selected research (more)

I am interested in 3D generative models, self-supervised learning, score-based models, graph neural networks, multi-task learning, and leveraging sparse priors for 3D reconstruction. I draw inspiration from intelligence in humans and nature while I attempt to solve multidisciplinary problems using machine learning. My goal is to develop advanced design tools, allowing intelligent agents to understand and improve existing 2D and 3D designs made by humans.

    publications

    1. octa.gif
      Multi-task Learning for Optical Coherence Tomography Angiography (OCTA) Vessel Segmentation
      Can KozOnat Dalmaz, and Mertay Dayanc
      Medical Imaging Meets NeurIPS, 2023
    2. DAC.gif
      Data Augmentation of Engineering Drawings for Data-Driven Component Segmentation
      IDETC-CIE, 2022
    3. manu.gif
      Flaw Detection in Metal Additive Manufacturing Using Deep Learned Acoustic Features
      ML4Eng @ NeurIPS, 2020

    selected projects (more)

    1. gen3d.png
      Text-to-3D and Image-to-3D made easy, Mar 2024
    2. cosona.png
      Co:Sona
      Chat to your favourite characters, Nov 2023
    3. physyou.png
      physyou
      Can KozYi ZuIan Perez, and Leslie Hwang
      Your AI-powered physical therapist, anywhere, Feb 2021
    4. covidanalyst.png
      COVID Analyst
      AI-powered targeted analytics for the COVID-19 pandemic, Apr 2020
    5. pocketanalyst.png
      PocketAnalyst
      PocketAnalyst puts the brain of financial analysts in your pocket to help you navigate the world of financial markets, Oct 2019

    code