Heejo Jeong

M.S in CS | Seeking Ph.D. Opportunities

Email: wjdgmlwh1629343@gmail.com

Phone: +82)10-3573-6274

About Me

 Hi, I’m Heejo Jeong. I graduated with an M.S. in Computer Graphics from Korea University, specializing in physics-based animation, and along the way I developed a passion for real-time graphics. I’m now looking for a Ph.D. program where I can help push the boundaries of realistic, interactive visual computing.
 You can find more details about my academic background and experience in my CV.

Education

Korea University, Seoul, Republic of Korea


M.S. in Computer Science & Engineering (Sep 2023 – Aug 2025)
 Advisor (M.S.): Prof. JungHyun Han

B.S. in Civil, Environmental & Architectural Engineering (Mar 2017 – Aug 2023)
B.S. in Artificial Intelligence (Interdisciplinary Program)

 Undergraduate period includes 2 years of mandatory military service

Publication

Momentum-preserving Inversion Alleviation for Elastic Material Simulation

Heejo Jeong, Seung-wook Kim, JaeHyun Lee, Kiwon Um, Min Hyung Kee, and JungHyun Han,
Computer Animation and Virtual Worlds (CAVW), Vol. 35, No. 3, May 2024, pp. e2249. DOI ·

Experience

Research Intern

Collaborated with Prof. Kiwon Um on differentiable physics and data-driven simulation methods.

at Télécom Paris, Institut Polytechnique de Paris, France (Jan 2025 ~ Feb 2025)

Military Service

Republic of Korea Army

(Aug 2020 ~ May 2022)

Projects

Learning Neural Hyper-elastic Constraints in XPBD Simulation, Thesis  

Demo 1 Demo 2 Demo 3

A neural network is inserted into the XPBD physics engine so it can learn realistic soft-body behaviour (like rubber or flesh) from just a few example motions, replacing tedious hand-tuned material formulas.

Stable Fluid 

Demo 1 Demo 2 Demo 3

A 2-D stable-fluid solver originally prototyped for an LG Electronics project on real-time air-conditioning airflow visualization in the metaverse. Implemented in Taichi for GPU-accelerated Conjugate gradient method

PCISPH(Predictive-Corrective Incompressible SPH) 


 

A practice example that implements the full Predictive-Corrective Incompressible SPH pipeline from scratch using only minimal data structures.