Woo Chul (Woochul) Shin

Hello! I'm Woo Chul, a master's student majoring in CS at Georgia Tech, where I am advised by Prof. Danfei Xu.

I earned my undergraduate degree at Seoul National University where I double majored in Artificial Intelligence and Economics.

Please feel free to check out my CV and drop me an email if you want to chat!

Email  /  Google Scholar  /  CV (Aug 2024)  /  LinkedIn  /  Github

Research

I'm interested in robotics, particularly in robot learning and dexterous manipulation, computer vision, and machine learning. My research focuses on enabling robots to perform dexterous manipulation in dynamic and complex environments, learning to perceive and interact with the world effectively. A key aspect of my work involves learning from human video demonstrations to teach robots nuanced manipulation skills and intuitive interactions, bridging perception and action in real-world scenarios.

ImMimic is an embodiment-agnostic co-training framework that bridges the domain gap between large-scale human videos and limited robot demonstrations. It uses Dynamic Time Warping to map human hand poses to robot joints and applies MixUp interpolation to generate intermediate domains for smoother domain adaptation. Evaluations across two parallel-jaw grippers (Robotiq, Fin Ray) and two dexterous hands (Ability, Allegro) demonstrate that ImMimic significantly improves task success and execution smoothness.

We propose SAIL (Speed-Adaptive Imitation Learning), a framework for enabling faster-than- demonstration execution of policies by addressing key technical challenges in robot dynamics and state-action distribution shifts. SAIL achieves up to a 4× speedup over demonstration speed in simulation and up to 3.2× speedup on physical robot.

We develop MimicLabs, a data generation framework to procedurally emulate key sources of diversity in robot datasets. Using this framework, we generate large-scale datasets with controlled variations to analyze how collection diversity and retrieval strategies impact downstream policy learning.

Work Experience

Software Development Engineer Intern, Amazon (May 2025 -- Aug. 2025)
Bellevue, WA

Research Assistant, Georgia Tech (Fall 2024 - Present)
Atlanta, GA
Lab: Robot Learning and Reasoning Lab
Advisor: Danfei Xu
Collaborator: Yunhai Han from STAR Lab

Software Engineer, Kakao (Jun. 2024 -- Jul. 2024)
South Korea
* Developed an Kubernetes-based ML platform for AI model training and inference.

Software Engineer, Kakao Brain (Aug. 2022 -- May. 2024)
South Korea
* Developed an Kubernetes-based ML platform from scratch for AI model training and inference.

Software Engineer Intern, Elysia (Mar. 2022 -- Jun. 2022)
South Korea
* Built backend server and smart contracts for a blockchain-based crowdfunding service.

Software Engineer Intern, Kakao Brain (Dec. 2021 -- May. 2022)
South Korea
* Built an AI resume creation service using GPT-2.

Software Engineer Intern, SNUAILAB (Dec. 2020 -- May. 2021)
South Korea
* Developed a YOLOv4-based image labeling system to annotate pig farm data.

Teaching Experience

CS4644/CS7643, Deep Learning, Georgia Tech
Spring 2025, Teaching Assistant

CS4644/CS7643, Deep Learning, Georgia Tech
Fall 2024, Teaching Assistant

M2177.007100, Field Application Research of Blockchain 2, SNU
Spring 2022, Teaching Assistant

M2177.007000, Field Application Research of Blockchain 1, SNU
Fall 2021, Teaching Assistant

Embodiment Experience