I am a Ph.D candidate advised by professor Jaegul Choo at KAIST Graduate School of AI. Previously, I interned at Meta Reality Labs and NAVER LABS as a Ph.D research intern.

My current research interest is to construct 3D generative models for physical AI, specifically through 3D world models via video diffusion and 3D neural representations. I am also interested in scaling these systems into Vision Language Action (VLA) models to enable foundation model-driven autonomy in complex driving environments.

Contact

  • shwang.14 [at] kaist.ac.kr

  • 8 Seongnam-daero 331 beon-gil, KINS Tower, Suite 904, Bundang-gu, Seongnam-si, Gyeonggi 13558, South Korea

Education

  • Ph.D | KAIST Graduate School of AI

    2022.02 - 2026.08 (expected)

    Advisor: Prof. Jaegul Choo

  • M.S | KAIST School of Electrical Engineering

    2020.02 - 2022.02

    Advisor: Prof. Hyun Myung

  • B.S | KAIST Dept. of Mechanical Engineering

    2014.08 - 2022.02

Professional Experiences

  • META logo
    Meta Reality Labs | Codec Avatars Team
    June 2025 - Nov. 2025
    Pittsburgh, USA

    Research Intern | Advisor: Timur Bagautdinov and Egor Zakharov
  • NAVER LABS logo
    NAVER LABS | Spatial AI Team
    July 2024 - Oct 2024
    Seongnam, Korea

    Research Intern | Advisor: Suyong Yeon

Publications

  • HumanAnything: Spatially-Aligned Multi-Modal Video Diffusion for Human-Centric Generation

    Sungwon Hwang, Egor Zakharov, Junxuan Li, Felix Taubner, Jin Kyu Kim, Itai Druker, Jaegul Choo, Timur Bagautdinov

    Under Review

    Project Page

  • SphereDiff: Tuning-free 360° Static and Dynamic Panorama Generation via Spherical Latent Representation

    Minho Park*, Taewoong Kang*, Jooyeol Yun, Sungwon Hwang, Jaegul Choo

    Association for the Advancement of Artificial Intelligence (AAAI), 2026, Oral Presentation

    Paper | Project Page | Code

  • SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel-based Head Avatars

    Jaeseong Lee*, Taewoong Kang*, Marcel C. Bühler, Min-Jung Kim, Sungwon Hwang, Junha Hyung, Hyojin Jang, Jaegul Choo

    The International Conference on Learning Representations (ICLR), 2025

    Paper | Project Page | Code

  • Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting

    Junha Hyung, Susung Hong, Sungwon Hwang, Jaeseong Lee, Jaegul Choo, Jin-Hwa Kim

    Advances in Neural Information Processing Systems (NeurIPS), 2024

    Paper | Project Page

  • VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors

    Sungwon Hwang*, Min-Jung Kim*, Taewoong Kang, Jayeon Kang, Jaegul Choo

    Proceedings of the European Conference on Computer Vision (ECCV), 2024

    Paper | Project Page | Code

  • FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

    Sungwon Hwang, Junha Hyung, Daejin Kim, Min-Jung Kim, Jaegul Choo

    Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2023

    Paper | Project Page

  • Local 3D Editing via 3D Distillation of CLIP Knowledge

    Junha Hyung, Sungwon Hwang, Daejin Kim, Hyunji Lee, Jaegul Choo

    Proceedings of the IEEE/CVF Converence on Computer Vision and Pattern Recognition(CVPR), 2023

    Paper | Code

  • Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network

    Sungwon Hwang, Hyungtae Lim, Hyun Myung

    The British Machine Vision Conference (BMVC), 2021

    Paper | Code

  • ERASOR: Egocentric Ratio of Psuedo Occupancy-based Dynamic Object Removal for Static 3D Point Cloud Map Building

    Hyungtae Lim, Sungwon Hwang, Hyun Myung

    IEEE Robotics and Automation Letters (RA-Letters)

    Paper | Code

  • Normal Distributions Transform is Enough: Real-time 3D Scan Matching for Pose Correction of Mobile Robot

    under Large Odometry Uncertainties

    Hyungtae Lim*, Sungwon Hwang*, Sungjae Shin, Hyun Myung (*: equal contribution)

    International Conference on Control, Automation and Systems (ICCAS), 2020

    Paper | Video

  • Text2Control3D: Controllable 3D Avatar Generation in Neural Radiance Fields using Geometry-Guided Text-to-Image

    Diffusion Model

    Sungwon Hwang, Junha Hyung, Jaegul Choo

    arXiv preprint

    Paper | Project Page | Code