Skip to content
View lloydkwak's full-sized avatar

Organizations

@nl-javastudy @DayAlgorithm

Block or report lloydkwak

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
lloydkwak/README.md

DongGeon (Lloyd) Kwak

Computer Science undergraduate at SeoulTech working on robot learning. I study how pretrained policies can adapt when a robot's body changes and recover from failures.

Website & research portfolio · CV · Email · LinkedIn

Selected work

Project Focus
FAVOR Training-free adaptation of diffusion policies to joint faults. Manuscript in preparation.
MTREA Embodiment adaptation and task retention for vision-language-action policies. Ongoing two-person capstone project.
MakeYourBrick From a single photo to a buildable LEGO model.
RL-Arena Competitive RL platform; environment package, match runner and backend.

For FAVOR, I receive research feedback from Prof. Ji-Hyeong Han and participate in weekly lab meetings.

Previously a software developer at Laver and CHASER. Co-inventor on Korean Patent 10-2647135 for real-time crack detection with mobile robots.

Pinned Loading

  1. FAVOR FAVOR Public

    Python 2

  2. MakeYourBrick MakeYourBrick Public

    image to ldr

    Python 4 1

  3. DeepDetection_2025 DeepDetection_2025 Public

    Jupyter Notebook 1