HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Thu, 18 Dec 2025 07:30:09 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"6943ad81-6988" expires: Sun, 28 Dec 2025 10:29:24 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 2B5E:2B0FD4:789318:870DB5:6951042B accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 10:19:24 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210095-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766917164.072848,VS0,VE203 vary: Accept-Encoding x-fastly-request-id: c0cc64c1f307c96a65e20e3b8daccb4e884d1e49 content-length: 7902

Jisu Nam

---

I am a fourth-year Ph.D. student at KAIST, advised by Seungryong Kim. I am closely working with Yang Zhou at Adobe Research through a couple of internships and collaborating with Junhwa Hur at Google DeepMind.

My research bridges visual perception and generation. I am interested in general perception for images and videos, particularly visual correspondence - image matching and point tracking. Recently, I have been working on large-scale image/video generative models, analyzing their representations in the context of correspondence - ultimately to understand, enhance, and manipulate the synthesis process.

I’d love to connect with people who share similar interests! Feel free to reach out via email!

Work Experience

---

Research Intern at Adobe Research, San Jose, CA (2025.05 - 2025.09)
Mentors: Yang Zhou, Yicong Hong, Chun-Hao Huang, Feng Liu
Project: Foundation Model for Infinite Interactive 3D Gaming Worlds

Research Intern at Adobe Research, San Jose, CA (2024.05 - 2024.08)
Mentors: Yang Zhou, Jing Shi, Difan Liu, Zhan Xu, Feng Liu
Project: Foundation Model for Consistent Full-Body Human Generation

Research Intern at Naver Cloud, Seoul, Korea (2023.04 - 2023.10)
Mentors: Seunggyu Chang, Heesu Kim, DongJae Lee
Project: Training-free Semantically Consistent Image Generation

Selected Publications

---

---

Emergent Temporal Correspondences from Video Diffusion Transformers

Jisu Nam^*, Soowon Son^*, Dahyun Chung, Jiyoung Kim, Siyoon Jin, Junhwa Hur^†, Seungryong Kim^†

NeurIPS 2025

Visual Persona: Foundation Model for Full-Body Human Customization

Jisu Nam, Soowon Son, Zhan Xu, Jing Shi, Difan Liu, Feng Liu, Aashish Misraa, Seungryong Kim^†, Yang Zhou^†

CVPR 2025

Local All-Pair Correspondence for Point Tracking

Seokju Cho, Jiahui Huang, Jisu Nam, Honggyu An, Seungryong Kim^†, Joon-Young Lee^†

ECCV 2024

DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization

Jisu Nam, Heesu Kim, DongJae Lee, Siyoon Jin, Seungryong Kim^†, Seunggyu Chang^†

CVPR 2024

Diffusion Model for Dense Matching

Jisu Nam, Gyuseong Lee, Sunwoo Kim, Hyeonsu Kim, Hyoungwon Cho, Seyeon Kim, Seungryong Kim

ICLR 2024, Oral (1.2% acceptance rate)

Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence

Sunghwan Hong, Jisu Nam, Seokju Cho, Susung Hong, Sangryul Jeon, Dongbo Min, and Seungryong Kim

NeurIPS 2022

Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation

Sunghwan Hong*, Seokju Cho*, Jisu Nam, Stephen Lin, Seungryong Kim

ECCV 2022

Honors

---

37th Workshop on Image Processing and Image Understanding, 2025
Best Paper Award

37th Workshop on Image Processing and Image Understanding, 2025
Best Poster Presentation Award

Qualcomm Innovation Fellowship, 2024
Winner

33th Artificial Intelligence and Signal Processing, 2023
Best Paper Award

Template of Lior Yariv