Hyemin Yang

KAIST, Daejeon, Korea

hyemin0806@kaist.ac.kr

hyeminy0716@gmail.com

I am a M.S. student at the Visual Intelligence Lab (VILAB), KAIST, advised by Prof. Kuk-Jin Yoon. I received my B.S. in Computer Science from DGIST in 2025.

My research focuses on building autonomous systems that are robust, efficient, and deployable in the real world. I am particularly interested in:

End-to-End Autonomous Driving (E2E-AD): Developing frameworks that generalize across diverse camera viewpoints and heterogeneous domains, including viewpoint-robust perception and multi-domain learning.
Vision-Language-Action (VLA) Models: Designing efficient inference architectures for robot manipulation that adaptively balance computation and performance.

Feel free to reach out via email at hyemin0806@kaist.ac.kr.

selected publications

NeurIPS
VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting

Hoonhee Cho, Jae-Young Kang, Giwon Lee, Hyemin Yang, Heejun Park, Seokwoo Jung, and Kuk-Jin Yoon

In Conference on Neural Information Processing Systems, 2025

Abs Bib HTML

End-to-end autonomous driving (E2E-AD) has emerged as a promising paradigm that unifies perception, prediction, and planning into a holistic, data-driven framework. However, achieving robustness to varying camera viewpoints, a common real-world challenge due to diverse vehicle configurations, remains an open problem. In this work, we propose VR-Drive, a novel E2E-AD framework that addresses viewpoint generalization by jointly learning 3D scene reconstruction as an auxiliary task to enable planning-aware view synthesis.
@inproceedings{cho2024vrdrive, title = {VR-Drive: Viewpoint-Robust End-to-End Driving with Feed-Forward 3D Gaussian Splatting}, author = {Cho, Hoonhee and Kang, Jae-Young and Lee, Giwon and Yang, Hyemin and Park, Heejun and Jung, Seokwoo and Yoon, Kuk-Jin}, booktitle = {Conference on Neural Information Processing Systems}, year = {2025}, }
arXiv
HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models

Hoonhee Cho, Giwon Lee, Jae-Young Kang, Hyemin Yang, Heejun Park, and Kuk-Jin Yoon

arXiv preprint, 2026

Abs Bib HTML

End-to-end autonomous driving (E2E-AD) has emerged as a compelling alternative to traditional modular pipelines. While recent approaches achieve strong performance on single-domain datasets, their performance degrades significantly when trained jointly across multiple heterogeneous domains. We propose HEAT, a trajectory-driven learning paradigm that organizes training around planning trajectories, enabling the model to capture domain-invariant representations of driving intent.
@article{yang2025heat, title = {HEAT: Heterogeneous End-to-End Autonomous Driving via Trajectory-Guided World Models}, author = {Cho, Hoonhee and Lee, Giwon and Kang, Jae-Young and Yang, Hyemin and Park, Heejun and Yoon, Kuk-Jin}, journal = {arXiv preprint}, year = {2026}, }