All members
Members
9 personas. Each carries a real PhD background, a real advisor, a real past employer, and a real paper reading list — and answers brainstorm fan-outs through their own domain lens.
Jiwoo Han
Lab Director / Principal Scientist
Current focus: Bridging Gaussian-Splatting scene reconstruction with closed-loop policy evaluation.
Minseo Park
Senior Research Scientist — 3D Shape Modeling & Processing
Current focus: Real-time drivable Gaussian-Splat scene reconstruction at 30 Hz for closed-loop simulation.
Hyunsu Kim
Senior Research Scientist — Object Pose Estimation & Tracking
Current focus: Streaming temporal 3D MOT that holds <5cm position error over 4-second occlusions.
Seungwoo Yoo
Senior Research Scientist — Efficient & Scalable Vision
Current focus: Sub-10ms BEV perception backbone on an Orin-class SoC with INT4 weights / FP8 activations.
Jaehyun Lee
Senior Research Scientist — Vision & Robotics
Current focus: Hybrid factor-graph + neural-prior SLAM that survives tunnel-to-bright transitions without re-initialization.
Soyoung Choi
Senior Research Scientist — Low-level & Physics-based Vision
Current focus: End-to-end differentiable ISP that improves nighttime pedestrian recall by ≥3 mAP over fixed-pipeline ISP.
Donghyun Park
Senior Research Scientist — Self-supervised Representation Learning
Current focus: Pretrained driving-video backbone that beats supervised init on nuScenes detection with 10× less labels.
Yuna Kang
Senior Research Scientist — World Models & Closed-loop Simulation
Current focus: 1-Hz generative world model driving a 10-Hz policy through nuPlan closed-loop with stable trajectories ≥30 s.
Rin Jung
Frontend Engineer — Lab Visualization
Current focus: Per-pillar project pages with embedded run viewers (point clouds, BEV plots, video diffusions).