Postdoctoral Research Fellow
Artificial Intelligence Institute (AIIS)
Seoul National University
jkim.aiforall@gmail.com
(+82)10-9844-9885

Research Fellow
OpenMind
San Francisco Bay Area
justin@openmind.com

About Me

I am a Physical AI Researcher.

Education

Seoul National University

Ph.D. in Artificial Intelligence
Advisor: Byoung-Tak Zhang
Thesis: Learning Semantically Grounded Latent Spaces in Vision-Language-Action Models
March 2021 – August 2026

Yonsei University

B.S. in Electrical and Electronic Engineering (EEE)
March 2016 – February 2021
Thesis: Large-Scale Tiny Face Detection using Multi-Task Cascaded Convolutional Neural Network

Publications

Highlights

Disentangling Spurious Correlations in Vision-Language-Action Models via Predicting Domain-Invariant Latent Lookahead

Junghyun Kim^*, Ngseo Kim^*, ChungWoo Lee, Seoyeon Lee, Woo-Jeong Baek, Adam Zhou, Chip Huyen, Jun-Ki Lee^†, Gi-Cheon Kang^†, Byoung-Tak Zhang^†
Conference on Robot Learning (CoRL 2026)
RSS 2026 SemRob (Spotlight)

CLIP-RT: Learning Language-Conditioned Robotic Policies from Natural Language Supervision

Gi-Cheon Kang^*, Junghyun Kim^*, Kyuhwan Shim, Jun Ki Lee^†, Byoung-Tak Zhang^†
Robotics: Science and Systems (RSS 2025)
CoRL 2024 Workshop on Language and Robot Learning Project Page Paper Github HuggingFace

All Publications

MicroVLA: Edge-Deployable Vision Language Action at 10M Parameters

Ngseo Kim, Junghyun Kim, Gi-Cheon Kang^†, Youngjae Yu^†, Byoung-Tak Zhang^†
RSS 2026 L2P workshop

PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments

Kihyun Kim, Chaeyun Kim, Jongho Shin, Taeyoun Kwon, Junghyun Kim, Mijin Koo, Haon Park
ECCV 2026 Workshop on Human-Motion World Models
Paper

RefineGround: From Noisy Similarity to Discriminative Grounding for Zero-shot Video Moment Retrieval

Jangha Lee, Junbin Xiao, Junghyun Kim, Byoung-Tak Zhang^†, Minjoon Jung^†
Under Review

Can Embodied Agents Remember What You Said? Evaluating Dialogue-Grounded Embodied Memory in 3D Environments

Seongjun Jeong, Junghyun Kim, Gi-Cheon Kang^†, Byoung-Tak Zhang^†
CVPR 2026 Workshop on 3D-LLM/VLA

EgoExo-Con: Exploring View-Invariant Video Temporal Understanding

Minjoon Jung, Junbin Xiao, Junghyun Kim, Byoung-Tak Zhang^†, Angela Yao^†
European Conference on Computer Vision (ECCV 2026)
NeurIPS 2025 Workshop on Multimodal Algorithmic Reasoning
Project Page Paper Github

Socratic Planner: Inquiry-Based Zero-Shot Planning for Embodied Instruction Following

Suyeon Shin, Sujin jeon^*, Junghyun Kim^*, Gi-Cheon Kang^*, Byoung-Tak Zhang
International Conference on Robotics & Automation (ICRA 2025)
Paper Code

PGA: Personalizing Grasping Agents with Single Human-Robot Interaction

Junghyun Kim, Gi-Cheon Kang^*, Jaein Kim^*, Seoyun Yang, Minjoon Jung, Byoung-Tak Zhang
International Conference on Intelligent Robots and Systems (IROS 2024)
Paper Code

PROGrasp: Pragmatic Human-Robot Communication for Object Grasping

Gi-Cheon Kang, Junghyun Kim, Jaein Kim, Byoung-Tak Zhang
International Conference on Robotics & Automation (ICRA 2024)
Paper Code

GVCCI: Lifelong Learning of Visual Grounding for Language-Guided Robotic Manipulation

Junghyun Kim, Gi-Cheon Kang^*, Jaein Kim^*, Suyeon Shin, Byoung-Tak Zhang
International Conference on Intelligent Robots and Systems (IROS 2023)
Oral Presentation Paper Code Poster Presentation Video Demo Video