Yigit Korkmaz

I am a first-year PhD student in Computer Science at University of Southern California. I am lucky to be advised by Prof. Erdem Biyik.

My Research interests lie in Robotics, Imitation Learning, Reinforcement Learning, Human-in-the-loop Learning, Human-Robot Interaction. I specifically focus on developing algorithms that enable AI agents to model the behaviors and goals of humans and other agents by leveraging different forms of information, including explicit forms such as human demonstrations and comparisons, and more implicit forms such as human gaze and gestures. My aim is to equip AI agents and robots with the capability to understand and align with humans' goals and preferences.

Previously, I worked with Prof. Xiaolong Wang on using Imitiation Learning for dexterous manipulation, and with Prof. Nikolay Atanasov on the effects of touch sensors in learning manipulation tasks. I started Machine Learning research with Prof. Burak Acar at Bogazici University.

Fun Fact: My name is pronounced as Yeet.

PhD. in Computer Science, University of Southern California 2023-present

Msc. in Electrical and Computer Engineering, UC San Diego 2021-2023

Bsc. in Electrical and Electronics Engineering, Bogazici University 2016-2021

Minor in Mechanical Engineering, Bogazici University 2017-2021

Feb 2024 - CyberDemo is accepted to CVPR 2024!

Aug 2023 - Started my PhD in Computer Science at University of Southern California!

June 2023 - Completed my Master's in ECE at UC San Diego.

September 2021 - Started UC San Diego for my Master's Degree in Electrical and Computer Engineering.

March 2021 - Started working as a Robotics Engineer at Kodmed.

February 2021 - Graduated from Bogazici University with a Bachelor's Degree in Electrical and Electronics Engineering!

July 2021 - Started working as a Artificial Intelligence / Computer Vision Engineer at senpai.gg.

Transformer networks are highly utilized in Natural Language Processing(NLP) tasks. In this project, the use of Longformer, which is a transformer based network with advanced attention mechanism, in classifying argumentative elements of students’ writing will be discussed.

In this project, APF(artificial potential fields), which a method used to formulate obstacle and goal interactions in a robot’s path, is implemented. With the assumption of a known map, obstacles act as repulsive forces where targets act as attractive ones. The code is written for ROS environment, and experimented on real robots.

In this repo, you can find the proposed solutions to weekly assignments given in Algorithms course from Princeton University, offered by Coursera. This repo gets updated with every new task completed.

Template is from Jon Barron's awesome website.