Youngjoon Jeong

I am a Ph.D. student in the Graduate School of Data Science at Seoul National University, advised by Taesup Kim. I received my B.S. and M.S. in Rural Systems Engineering (Agricultural Engineering) from Seoul National University. I am broadly interested in physical AI and world models.

Email  /  CV  /  Scholar  /  Github  /  LinkedIn  /  X

News

• Jun 2026 Two preprints, PoLAR and J-PARC, are now available on arXiv.
• Feb 2026 VILA was accepted to CVPR 2026.
• Jan 2026 Sparse Imagination was accepted to ICLR 2026.

Research Interests

My research focuses on representation learning for physical AI, especially latent actions and world models for robot policy learning, visual planning, and robust embodied decision-making.

Publications

	PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning Youngjoon Jeong, Jihwan Yu, Minsoo Jo, Junha Chun, Taesup Kim arXiv preprint, 2026 project page / arXiv / code
	Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults Minsoo Jo, Taeju Kwon, Junha Chun, Youngjoon Jeong, Taesup Kim arXiv preprint, 2026 arXiv
	Learning to Act Robustly with View-Invariant Latent Actions Youngjoon Jeong*, Junha Chun*, Taesup Kim   (* Equal Contribution) The IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026 project page / arXiv
	Sparse Imagination for Efficient Visual World Model Planning Junha Chun*, Youngjoon Jeong*, Taesup Kim   (* Equal Contribution) International Conference on Learning Representations, 2026 project page / OpenReview / arXiv
	Object-centric world model for language-guided manipulation Youngjoon Jeong*, Junha Chun*, Soonwoo Cha, Taesup Kim   (* Equal Contribution) ICLR World Model Workshop, 2025 arXiv
	Piecewise physics-informed neural networks for surrogate modelling of non-smooth system in elasticity problems using domain decomposition Youngjoon Jeong*, Sang-ik Lee*, Jong-hyuk Lee, Won Choi   (* Equal Contribution) Biosystems Engineering, 2025 journal
	Data-efficient surrogate modeling using meta-learning and physics-informed deep learning approaches Youngjoon Jeong, Sang-ik Lee, Jong-hyuk Lee, Won Choi Expert Systems with Applications, 2024 journal
	Development of numerical land surface temperature model of Jeju Island, South Korea based on finite element method Youngjoon Jeong, Sang-ik Lee, Jong-hyuk Lee, Seon Deok Jin, Se Hwan Son, Won Choi Environmental Earth Sciences, 2021 journal

This website was forked from here.