Seoul National University (SNU)
Sep. 2023 - Present, CSE, Integrated M.S. and Ph.D. (Adviser: Jaesik Park)

Pohang University of Science and Technology (POSTECH)
Feb. 2019 - Feb. 2023, CSE, B.S. (Summa Cum Laude)

NVIDIA (Spatial Intelligence Lab)
June 2026 - Dec. 2026, Research Scientist Intern / Santa Clara, CA (Planned)

Stealth Startup
Feb. 2026 - June 2026, Research Scientist Intern / Remote from Seoul
Working with Xun Huang on video world models

Carnegie Mellon University (Robotics Institute)
Oct. 2025 - Jan. 2026, Visiting Researcher (Jun-Yan's Lab) / Pittsburgh, PA
Worked with Ruihan Gao, Ava Pun, Wenzhen Yuan, and Jun-Yan Zhu on generative AI for accessibility

Adobe Research
June 2025 - Sep. 2025, Research Scientist Intern / San Francisco, CA
Worked with Xun Huang, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, and Eli Shechtman on building fast and interactive video generative models (MotionStream)

Direct Reward Fine-Tuning on Poses for Single Image to 3D Human in the Wild
Seunguk Do, Minwoo Huh, Joonghyuk Shin, Jaesik Park
ICLR 2026 - [Coming soon | TL;DR ▼] We introduce DRPOSE, a direct reward fine-tuning method that improves pose accuracy in single-view 3D human reconstruction, especially for dynamic and acrobatic poses, without requiring expensive 3D human assets.

MotionStream: Real-Time Video Generation with Interactive Motion Controls
Joonghyuk Shin, Zhengqi Li, Richard Zhang, Jun-Yan Zhu, Jaesik Park, Eli Shechtman, Xun Huang
ICLR 2026 - [Paper | Project Page | Code | TL;DR ▼] MotionStream is a streaming (causal, real-time, and long-duration) video generation system with motion controls, operating at ~30 FPS on a single H100 GPU, unlocking new possibilities for interactive content generation.

JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching
Mingi Kwon*, Joonghyuk Shin*, Jaeseok Jung, Jaesik Park†, Youngjung Uh†
arXiv 2025 - [Paper | Project Page | TL;DR ▼] We present a unified framework that jointly generates synchronized facial motion and speech using flow matching and MM-DiT, enabling diverse audio-visual synthesis tasks within a single model.

Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing
Joonghyuk Shin, Alchan Hwang, Yujin Kim, Daneul Kim, Jaesik Park
ICCV 2025 - [Paper | Project Page | Code | TL;DR ▼] We perform a systematic analysis of MM-DiT's bidirectional attention mechanism and introduce a robust prompt-based editing method working across diverse MM-DiT models (SD3 series and Flux).

InstantDrag: Improving Interactivity in Drag-based Image Editing
Joonghyuk Shin, Daehyeon Choi, Jaesik Park
SIGGRAPH Asia 2024 - [Paper | Project Page | Code (230+) | TL;DR ▼] We present InstantDrag, an optimization-free pipeline for fast, interactive drag-based image editing that requires only an image and drag instruction as input, learning from real-world video datasets.

Fill-Up: Balancing Long-Tailed Data with Generative Models
Joonghyuk Shin, Minguk Kang, Jaesik Park
arXiv 2023 - [Paper | Project Page | TL;DR ▼] We propose a two-stage method for long-tailed (LT) recognition using textual-inverted tokens to synthesize images, achieving SOTA results on standard benchmarks when trained from scratch.

StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis
Minguk Kang, Joonghyuk Shin, Jaesik Park
TPAMI 2023 - [Paper | Code (3500+) | TL;DR ▼] We present StudioGAN, a comprehensive library for GANs that reproduces over 30 popular models, providing extensive benchmarks and a fair evaluation protocol for image synthesis tasks.