Yongjun Cho
A Senior Research Scientist at WoRV (World model for Robotics and Vehicle control) team of Maum AI, I have 3 years and 7 months of experience in the AI startup industry. I completed a master's program at the School of Electrical Engineering of Korea Advanced Institute of Science and Technology (KAIST) advised by Dong Eui Chang, specializing in Artificial Intelligence and Reinforcement Learning.
My research aims to achieve robust generalization in robotics by integrating Vision-Language-Action (VLA) models with large-scale physical interaction data. Currently, I am bridging the gap between research and real-world deployment by developing commonsense-aware navigation systems, while actively expanding these generalizable methodologies to robotic manipulation. My work addresses fundamental challenges in robot learning, including Sim-to-Real transfer and data efficiency. Furthermore, I am dedicated to accelerating robot learning by releasing open-source benchmarks and datasets, and fostering a research ecosystem that is accessible across diverse robotic hardware.
Research Interest: Robotics, Autonomous Navigation, Imitation Learning, Reinforcement Learning, Vision-Language-Action Models, Generalization in AI
✉️ cyjun0304@kaist.ac.kr
News
Publications
[2]Daeseok Lee†, Yongjun Cho†
Fine-tuning Pocket-conditioned 3D Molecule Generation via Reinforcement Learning
ICLR 2024 Workshop on Generative and Experimental Perspectives for Biomolecular Design (GEM)
[3]Yongjun Cho†, Jae-Hyeon Park†, Jaesoon Choi, , Dong Eui Chang*
Sim-to-Real Transfer of Image-Based Autonomous Guidewire Navigation Trained by Deep Deterministic Policy Gradient with Behavior Cloning for Fast Learning
2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
[4]Yongjun Cho, Jae-Hyeon Park, Jaesoon Choi, , Dong Eui Chang*
Image Processing Based Autonomous Guidewire Navigation in Percutaneous Coronary Intervention
2021 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)
[5]Jae-Hyeon Park, Yongjun Cho, Jin-Yeong Jeong, , Dong Eui Chang*
Real-time Quadrotor Actuator Fault Detection and Isolation Using Multivariate Statistical Analysis Techniques with Sensor Measurements
2020 20th International Conference on Control, Automation and Systems (ICCAS)
Experience
Senior Research Scientist @ Maum AI
Seongnam, S.Korea · Nov. 2024 - Present
- Established a commercial pipeline for VLA navigation models (1B--7B), optimizing large-scale training and inference efficiency.
- Enhanced Sim-to-Real transfer and policy performance via domain randomization and efficient human intervention pipelines.
- Led open-source initiatives by releasing benchmarks, datasets, and simulation tools to accelerate robot learning.
Research Scientist @ Maum AI
Seongnam, S.Korea · May 2024 - Oct. 2024
- Led the ideation and fundamental research for commonsense-aware navigation systems CANVAS.
- Designed comprehensive evaluation protocols spanning Nvidia Isaac Sim and real-world environments.
- Developed the foundational pipeline for large-scale data collection, and model training.
Machine Learning Researcher @ Deargen Inc.
Seoul, S.Korea · Apr. 2022 - Apr. 2024
- Developed the overall Drug Target Interaction (DTI) model architecture and conducted data crawling and processing.
- Created a fine-tuning framework and provided services to an international big pharma corporation.
- Developed a reinforcement learning model to enhance pocket-conditioned 3D molecule generation model.
Education
M.S. in Electrical Engineering
KAIST (Korea Advanced Institute of Science and Technology) · Daejeon, S.Korea · Mar. 2020 - Mar. 2022
- Advisor: Dong Eui Chang
- Developed autonomous guidewire navigation systems using Reinforcement Learning and Sim-to-Real transfer.
- Led multiple autonomous drone projects, including vision-only navigation and custom radio control systems. Conducted R&D with HD Korea Shipbuilding to develop ship assistance drones featuring relative path planning and AI-driven perception.
- Investigated real-time anomaly detection for quadrotor actuators using multivariate statistical analysis.
- Awarded the Grand Prize in the Autonomous Drone Competition hosted by the Defense Acquisition Program Administration (DAPA).
B.S. in Department of Mechanical Engineering
KAIST (Korea Advanced Institute of Science and Technology) · Daejeon, S.Korea · Mar. 2015 - Mar. 2020
- Development of an Autonomous Driving Robot for Library Inventory Management as a Graduation Project
Honors & Awards
Outstanding Paper Awards
NeurIPS 2024 Workshop Open-World Agents
Vancouver, Canada
International
2024
Grand Prize
Autonomous Drone Competition hosted by the Defense Acquisition Program Administration
Daejeon, S.Korea
Domestic
2020
National Excellence Scholarship (Natural Sciences and Engineering)
Covers admission fee, full tuition, and additional support for study grant and living expenses
Korea Student Aid Foundation (KOSAF)
Scholarship
2015 - 2018