Hyunsoo Lee

Undergraduate student, Seoul National University

hyunsoolee.jpg

I am an undergraduate student in Electrical and Computer Engineering, double majoring in Mathematical Sciences at Seoul National University (SNU). I am currently a research intern at the SNU Machine Perception and Reasoning Lab, advised by Prof. Jonghyun Choi. Before that, I was a visiting student and research intern at UC Irvine, where I worked with Prof. Stephan Mandt, and I also conducted research at SNU with Prof. Young Min Kim and Prof. Bohyung Han. I am seeking Ph.D. positions starting in Fall 2027.

Research Vision

My work has focused on generative visual computing, where images, video, point clouds, human motion, and 3D geometry are treated as structured visual signals that can be controlled, synchronized, and extended across tasks. This line of work has appeared in leading computer vision and machine learning conferences including NeurIPS, CVPR, ECCV, ICML, and WACV.

My current direction moves from controlling generation toward understanding learning itself. I am beginning a new research agenda on neuroscience-inspired AI – using ideas from memory operations to study how artificial neural networks learn and generalize. I see this could be a path toward training and learning mechanisms that are not only stronger, but also more interpretable and adaptable.

The long-term question I care about is how to build intelligence that can solve problems beyond current human capability. My research so far has focused generative modeling as a lens for studying how systems form and manipulate representations. By connecting it with neuroscience-motivated ideas and continual learning, I aim to study the fundamentals of learning mechanisms. The broader goal is to build systems whose mechanisms can be explained and scaled toward more general intelligence.

News

Jul 2026 I’m attending ICML 2026, presenting the poster “Calibrated Test-Time Guidance for Bayesian Inference”.
Jun 2026 One paper accepted to ECCV 2026: “Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation”.
Jun 2026 I joined SNU Machine Perception and Reasoning Lab as a research intern.
Jun 2026 I’m attending CVPR 2026, presenting two papers: Geometric Stylization and ScaleEdit.

Publications

* denotes equal contribution. † denotes corresponding author.

  1. syncvc.png
    Variational Test-time Optimization for Diffusion Synchronization
    Under review, 2026
    Interprets collaborative generation as controlled sampling and optimizes test-time controls so multiple diffusion trajectories remain coherent while staying close to pretrained priors.
  2. alm.gif
    Accelerated Likelihood Maximization for Diffusion-based Versatile Content Generation
    Hyunsoo LeeInwoo Hwang, and Young Min Kim
    In ECCV, 2026
    Turns pretrained generative models into versatile content generators by optimizing unobserved regions during sampling across images, motion, video, and 3D domain.
  3. calibrated-guidance.png
    Calibrated Test-Time Guidance for Bayesian Inference
    In ICML, 2026
    Identifies why prior works on diffusion guidance can be posterior-miscalibrated and develops consistent estimators for Bayesian posterior sampling.
  4. geostyle.png
    Image-Guided Geometric Stylization of 3D Meshes
    In CVPR, 2026
    Uses Score Distillation Sampling (SDS) loss as geometry-aware deformation signals for reference-guided 3D mesh stylization beyond texture transfer.
  5. scaleedit.png
    Low-Resolution Editing is All You Need for High-Resolution Editing
    Junsung Lee*Hyunsoo Lee*Yong Jae Lee, and Bohyung Han
    In CVPR, 2026
    Scales image editing beyond 1K by using low-resolution edits as semantic references while transferring high-resolution details through synchronized patch optimization.
  6. point2pose.png
    Point2Pose: A Generative Framework for 3D Human Pose Estimation with Multi-View Point Cloud Dataset
    Hyunsoo LeeDaeum Jeon, and Hyeokjae Oh
    In WACV, 2026
    Frames 3D human pose estimation from raw point clouds as conditional generation and builds a pose framework using diffusion and flow matching.
  7. syncsde.png
    SyncSDE: A Probabilistic Framework for Diffusion Synchronization
    Hyunjun Lee*Hyunsoo Lee* , and Sookwan Han
    In CVPR, 2025
    Explains why diffusion synchronization works, identifies where correlation should be introduced, and unifies collaborative generation across images, motion, and 3D.
  8. oig.png
    Diffusion-Based Conditional Image Editing through Optimized Inference with Guidance
    Hyunsoo LeeMinsoo Kang, and Bohyung Han
    In WACV, 2025
    Introduces a tailored guidance mechanism for diffusion-based image editing, improving training-free text-driven edits while preserving source layout.
  9. csg.png
    Conditional Score Guidance for Text-Driven Image-to-Image Translation
    Hyunsoo Lee*Minsoo Kang*, and Bohyung Han
    In NeurIPS, 2023
    Derives a source-aware conditional score and attention mixup strategy for diffusion-based image editing, enabling prompt-specified region manipulation while preserving source-invariant content.

Education

Seoul National University Mar 2021 - Aug 2027 (Expected)
Seoul, Korea
B.S. in Electrical and Computer Engineering; Double Major in Mathematical Sciences
  • Compulsory military service included (Aug 2023 - Feb 2025).
University of California, Irvine Jan 2026 - Jun 2026
Irvine, CA
Computer Engineering, UC Education Abroad Program
Hansung Science High School Mar 2018 - Feb 2021
Seoul, Korea
  • Early visual understanding projects formed the origin of my research in computer vision.

Research Experience

Seoul, Korea
Research Intern
  • Advisor: Jonghyun Choi
  • Conducting research on neuroscience-motivated memory mechanisms for representation learning.
UC Irvine Mandt Lab Jan 2026 - Jun 2026
Irvine, CA
Research Intern
  • Advisor: Stephan Mandt
  • Conducted research on guidance methods for diffusion models in inverse problems and collaborative generation.
SNU 3D Vision Lab Mar 2025 - Nov 2025
Seoul, Korea
Research Intern
  • Advisor: Young Min Kim
  • Conducted research on geometry deformation and versatile content generation with diffusion models.
SNU Computer Vision Lab Jan 2023 - Aug 2023
Seoul, Korea
Research Intern
  • Advisor: Bohyung Han
  • Conducted research on training-free, diffusion-based image-to-image translation.

Awards and Honors

Korean Institute of Communication Sciences (KICS) Scholarship ($650)
Jun 2026
Korea-U.S. Advanced Technology Youth Exchange Program Scholarship ($9,000)
Dec 2025
SNU College of Engineering Creative Design Fair (Silver Prize, Research Track)
Sep 2025
Presidential Science Scholarship ($3,600)
Mar 2025
Young Engineers Honor Society (YEHS), an honor society under NAEK
Mar 2025 - Present
SNU Tomorrow's Edge Membership (STEM), an honor society of SNU Engineering
Mar 2025 - Present
Google Student Travel Grant ($1,500), financial support for attending WACV 2025
Mar 2025
SNU Earth Science Online Hackathon (3rd Prize, $2,000), tackling scientific problems with AI
Sep 2022
SNU Merit-based Scholarship, scholarship for high-GPA students
Aug 2021 - Mar 2025

Academic Services

Reviewer NeurIPS (2025-2026), ICLR (2026), ECCV (2026), TIP (2026)
Assistant TA Introduction to Circuit Theory and Laboratory (2023)

More

Collaboration

I am grateful to all collaborators from both ongoing and previous projects. I'm also open to new collaborations.

Collaboration

Posts

Notes for sharing useful knowledge, research ideas, and personal thoughts.

Posts