Suhyeok Jang

About

I am an M.S./Ph.D. student in the Algorithmic General Intelligence Laboratory (AGI-LAB), advised by Prof. Jinwoo Shin. I received my B.S. in Industrial and Management Engineering from Korea University in 2024. My research focuses on robot learning and World Action Models, particularly leveraging video generation models for synthetic robot data generation and adapting them into policies for robot control. Previously, I worked on test-time scaling for Vision-Language-Action models (VLAs) and adversarial robustness in image classification.

Publications

Authors *Equal contribution †Project Leads §Research Leads

Paper type CConference JJournal WWorkshop TTechnical Report PPreprint

W1CoRL 2026 G2A WorkshopOral

RoboCurate: Harnessing Diversity with Action-Verified Synthetic Data for Robot Learning

Seungku Kim*, Suhyeok Jang*, Byungjun Yoon, Dongyoung Kim, John Won, Jinwoo Shin

CoRL 2026 Workshop: From Generative Models to Robot Actions (G2A), Oral

Paper arXiv Website

P2Preprint 2026

Synthesizing Dexterous Robot Demonstrations from Human Videos via Virtual Try-On

Seungyong Lee, Suhyeok Jang, Minyoung Kim, Jinwoo Shin

arXiv, 2026

Paper arXiv Website Code Checkpoints Demo

P1Preprint 2026

Self-Distilling Future Video Representations for World Action Models

Huiwon Jang*, Suhyeok Jang*, Hyeonmo Kang, Seungku Kim, Jinwoo Shin, Sihyun Yu

arXiv, 2026

Paper arXiv Website Code Checkpoints X

T1Tech Report 2026

RLDX-1: A Dexterity-First Foundation Model for Robot Hands

Dongyoung Kim§, Huiwon Jang§, Myungkyu Koo†, Suhyeok Jang†, Taeyoung Kim†, et al., Jinwoo Shin§

RLWRLD Technical Report, 2026

Paper arXiv Website Code Checkpoints

C1ICLR 2026

Verifier-free Test-Time Sampling for Vision-Language-Action Models

Suhyeok Jang, Dongyoung Kim, Changyeon Kim, Youngsuk Kim, Jinwoo Shin

International Conference on Learning Representations (ICLR), 2026

Paper arXiv Website

J1TMLR 2024

Confidence-aware Denoised Fine-tuning of Off-the-shelf Models for Certified Robustness

Suhyeok Jang*, Seojin Kim*, Jinwoo Shin, Jongheon Jeong

Transactions on Machine Learning Research (TMLR), 2024

Paper arXiv Code

Education

Sep. 2024 - Current
Korea Advanced Institute of Science and Technology (KAIST)
M.S./Ph.D. Student in Graduate School of Artificial Intelligence
Mar. 2018 - Aug. 2024
Korea University
B.S. in Industrial and Management Engineering

Experience

Mar. 2026 - Current
Visiting Researcher
RLWRLD
Mar. 2024 - Aug. 2024
Undergraduate Researcher
Algorithmic Intelligence Laboratory (ALIN-Lab) (advised by Prof. Jinwoo Shin)
Nov. 2023 - Mar. 2024
Undergraduate Researcher
Universal Transfer Learning (UTL) Lab (advised by Prof. Donghyun Kim)
Mar. 2023 - Aug. 2023
Research Intern
NCSOFT Speech AI Lab

Academic Services

Conference Reviewer, NeurIPS'26, ICLR'27

Honors & Awards

1st Award in the 2023 K-Data Science Hackathon, Ministry of Science and ICTNov. 2023
Dean’s List, Korea University2nd 2023