Youngwoong Cho

Generalizable robot policy: from one dexterous hand to another, and from human demonstrations to robots.

M.S. Robotics student at Georgia Tech in Prof. Danfei Xu's Robot Learning and Reasoning Lab. Previously a Research Engineer at RLWRLD, adapting robot foundation models to dexterous hands.

Projects

Seven robot hands following the same fingertip targets.

One Action Interface, Seven Dexterous Hands

Can a policy trained on several robot hands control a hand it has never seen?

Frames from my egocentric Aria-glasses demonstration of a two-handed basket carry.

What Makes Retargeted Demonstrations Learnable?

Retargeting the same human demonstrations in two different ways gave policies with very different success rates. I want to know which properties of the retargeted actions cause that.

Adapting Robot Foundation Models to a 16-DoF Hand

At RLWRLD I worked on getting large pretrained policies (GR00T N1.6, π0.5, and a 3D geometry-aware policy) to work on DexJoCo, a public benchmark with 11 dexterous manipulation tasks.

Experience

  1. Aug 2026 – present

    Georgia Tech, Robot Learning and Reasoning Lab (RL2)

    Graduate Researcher, advised by Prof. Danfei Xu · Atlanta, GA

    Cross-embodiment dexterous manipulation and learning from retargeted demonstrations.

  2. Apr – Aug 2026

    RLWRLD

    Research Engineer · Seoul, Korea

    Adapted robot foundation models (GR00T N1.6, π0.5, GAM) to dexterous hands and built the training and evaluation platform.

  3. Mar – Aug 2022

    Naver Labs

    Deep Learning Research Intern, Autonomous Driving · Seongnam, Korea

    RL and imitation learning for 3D annotation, and a 3D annotation tool for collecting human demonstrations.

  4. May 2021 – Mar 2022

    Seoul Robotics

    Machine Learning Research Engineer Intern · Seoul, Korea

    LiDAR perception: curb detection, multi-view annotation tools, and the evaluation pipeline.

  5. May – Jul 2020

    Seoul National University, Interactive & Network Robotics Lab

    Research Intern, Prof. Dongjun Lee · Seoul, Korea

    Cooperative manipulation on a physical multi-robot testbed.

Education

  1. Expected May 2028

    Georgia Institute of Technology

    M.S. in Robotics

  2. 2023

    The Cooper Union

    B.E. in Mechanical Engineering, Minor in Computer Science, Summa Cum Laude