Research Statement
My research interests lie in Computer Vision, Generative AI, and World Models.
I am interested in building models that can understand, simulate, and interact with dynamic visual worlds across video and 3D/4D environments, with a focus on long-horizon generation and world dynamics.
- World Modeling β learning structured representations of states, entities, and dynamics from visual observations.
- Long-Horizon Generation β generating coherent and controllable visual worlds over extended temporal horizons.
|
NewsποΈ
π₯ (Apr. 2026) Our paper, Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-Spectrogramsis accepted at ICIP 2026.
π₯ (Feb. 2026) Invited to review for CVPR, ECCV, ICIP 2026.
π₯ (Sep. 2025) I started PhD at Rutgers University!
π₯ (Aug. 2025) Our paper, Revisiting Your Memory, is accepted for the Oral Paper at ACM Multimedia 2025 - CogMAEC Workshop.
π₯ (Jul. 2025) Invited as a reviewer from Computers in Industry.
π₯ (Feb. 2025) Invited as a reviewer from Pattern Recognition and IEEE Computational Intelligence Magazine.
π₯ (Oct. 2024) Our team won the Grand Prize at the AI & Art Hackathon and presented the work at the ART DIFFUSION, SNU MoA.
|
Education
Rutgers University
Sep. 2025 - Present
Ph.D. in Computer Science (Advisor: Vladimir Pavlovic)
Seoul National University
Mar. 2021 - Aug. 2023
M.S. in Brain and Cognitive Sciences (Advisor: Jiook Cha)
Ewha Womans University
Mar. 2017 - Feb. 2021
B.S. in Computer Science and Engineering
|
|
|
Compositional Brain Decoding via Visual Constituent Recombination
S. Kim*, J. Kwon*, J. Kwon,
Z. Cui, V. Pavlovic, M. Park, and J. Cha
Under Review, 2027
|
|
|
Stylus: Repurposing Stable Diffusion for Training-Free Music Style Transfer on Mel-Spectrograms
H. Wang*, J. Kwon*, S. Kim*, J. Seo, S. Yoo, Y. Lin and J. Cha
ICIP, 2026
[paper]
|
|
|
Revisiting Your Memory: Reconstruction of Affect-Contextualized Memory via EEG-guided Audiovisual Generation
J. Kwon*, H. Wang*, J. Yi*, S. Kim*,
S. Yoo, Y. Lin and J. Cha
ACM MM CogMAEC 2025 (CogMAEC), Oral Presentation
[paper]
|
|
|
AesFA: An Aesthetic Feature-Aware Arbitrary Neural Style Transfer
J. Kwon*, S. Kim*, S. Yoo, Y. Lin and J. Cha
AAAI 2024,
[project page][paper]
|
|
|
Macro2Micro: Cross-modal Magnetic Resonance Imaging Synthesis Leveraging Multi-scale Brain Structures
S. Kim*, J. Kwon*, J. Kwon*, J. Min, S. Bae,
S. Yoo, Y. Lin and J. Cha
arXiv, 2024
[paper]
|
Peer Review
Conference
CVPR, ICIP, NeurIPS, ICLR
Journal
Pattern Recognition, Computers in Industry, IEEE Computational Intelligence Magazine
|
Honors & Awards
Rutgers Department of Computer Science Excellent Teaching Assistant Award , 2026
Grand Prize at AI x Art Hackathon, Oct 2024
BrainKorea21 Four Scholarship, 2021β2022
2020 4th Seoul Innovation Challenge, Jan 2020 β Sep 2020
The 9th Ewha Festival for Business Plan, Mar 2019 β Dec 2019
EWHA Scholarship, 2018-2020
EWHA Merit-Based Scholarship (full tuition) - Awarded to the top 10% of students upon admission, 2017
|
|
|
I like swimming a lot, and funnily enough, my first name, "μμ (Sooyoung)," is pronounced exactly the same as "swimming" in Korean.
I also love movies and dramas with dynamic stories, I am especially a big fan of The Good Place, Brooklyn Nine-Nine, and Harry Potter series. I really love both discussing movie interpretations and imagining alternative movie endings with other people.
|
|
|
And finally, meet Choma (μ΄λ§), my beloved cat and unofficial research companion. π
|
|
