Seunghyeon Lee

prof_pic.jpg

I am an M.S. student at POSTECH, South Korea, advised by Prof. Minsu Cho at Computer Vision Lab.

My primary research interest is Embodied AI, focusing on intelligent systems that interact with the physical world. To enable such embodied intelligence, I leverage Generative AI and 3D Computer Vision as core foundations.

Ultimately, I aim to design machines that understand and interact with the world in a human-like manner.

Email : [email protected]

News

Feb 23, 2026 👩‍🎓 Joined POSTECH CVLab as a graduate student
Feb 22, 2026 ✨ Affostruction is accepted to CVPR 2026
Nov 11, 2025 ✨ CountSteer is accepted to AAAI 2025 RSD workshop
Sep 29, 2025 ✨ FreeAction is accepted to CoRL 2025 LSRW workshop

Publications

2026

  1. Affostruction: 3D Affordance Grounding with Generative Reconstruction
    Chunghyun Park, Seunghyeon Lee, and Minsu Cho
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    arXiv HTML PDF

2025

  1. FreeAction: Training-Free Techniques for Enhanced Fidelity of Trajectory-to-Video Generation
    Seungwook Kim, Seunghyeon Lee, and Minsu Cho
    In Conference on Robot Learning (CoRL) Workshop on Learning to Simulate Robot Worlds, 2025
    arXiv PDF
  2. CountSteer: Steering Attention for Object Counting in Diffusion Models
    Hyemin Boo*, Hyoryung Kim*, Myungjin Lee*, Seunghyeon Lee*, Jiyoung Lee, Jang-Hwan Choi, and Hyunsoo Cho
    In AAAI Workshop on Shaping Responsible Synthetic Data in the Era of Foundation Models, 2025
    * Equal contribution. Authors are listed in alphabetical order.
    arXiv PDF