Junseo Bang

Hi! I am a Ph.D. candidate working at the intersection of optical imaging and generative AI. I develop diffusion/flow-based methods for solving inverse problems in imaging (advisor: Prof. Se Young Chun, Intelligent Computational Imaging Lab). Previously, I worked on advanced imaging systems with nanophotonic/metasurface technologies (advisors: Prof. Byoungho Lee, Prof. Yoonchan Jeong, Optical Engineering and Quantum Electronics Lab).

đź’ˇ Research interest: closing the gap between optical system design and learned signal reconstruction, developing next-generation intelligent imaging systems that integrate physics and machine intelligence.

Publications ↓
profile.jpg

Junseo Bang

Ph.D. Student @ SNU ICL

📍 Seoul, South Korea

Recent News

May 26, 2026 An updated version of our paper “Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution” is now available on arXiv. The code will be released soon.
May 01, 2026 Our paper “Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules” accepted to ICML 2026.
Jun 09, 2025 Our paper “Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution” preprint released on arXiv.
May 12, 2025 Our paper AIM 2024 Challenge on UHD Blind Photo Quality Assessment accepted to ECCV 2024 Workshops.
Mar 29, 2025 Our paper “Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation” preprint released on arXiv.
Mar 10, 2025 Our paper accepted to ACS Photonics.
Feb 18, 2025 Our paper “Few-Shot Arbitrary Super-Resolution Considering Consistency and Realness” accepted to ICEIC 2025.
Oct 30, 2024 Our paper accepted to Science Advances.
Aug 27, 2024 Our paper accepted to Nano Letters.
Jul 30, 2024 Our paper accepted to ACS Photonics.

Publications

2026

  1. ICML 2026
    TriPS.gif
    Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
    Junseo Bang*, Dong Ju Mun*, Hoigi Seo, Seongmin Hong, and Se Young Chun
    In International Conference on Machine Learning (ICML), 2026

2025

  1. arXiv
    CasArbi.gif
    Self-Cascaded Diffusion Models for Arbitrary-Scale Image Super-Resolution
    Junseo Bang*, Joonhee Lee*, Kyeonghyun Lee*, Haechang Lee, Dong Un Kang, and Se Young Chun
    arXiv preprint, 2025
  2. arXiv
    TokeBi.gif
    Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation
    Hoigi Seo*, Junseo Bang*, Haechang Lee*, Joohoon Lee, Byung Hyun Lee, and Se Young Chun
    arXiv preprint, 2025
  3. ACS Photonics
    Janus.gif
    Cascaded Janus Meta-Optics: Generalized Platform for Bidirectional Asymmetric Modulation of Light
    Junseo Bang, Youngjin Kim, Taewon Choi, Changhyun Kim, Hyunwoo Son, Sun-Je Kim, Yoonchan Jeong, and Byoungho Lee
    ACS Photonics, 2025

2024

  1. Science Advances
    FoldedCamera.gif
    Metasurface Folded Lens System for Ultrathin Cameras
    Youngjin Kim*, Taewon Choi*, Gun-Yeal Lee, Changhyun Kim, Junseo Bang, Junhyeok Jang, Yoonchan Jeong, and Byoungho Lee
    Science Advances. Featured in Phys.org , 2024
  2. Nano Letters
    AchroGrating.gif
    Multiwavelength Achromatic Deflector in the Visible Using a Single-Layer Freeform Metasurface
    Taewon Choi, Chulsoo Choi, Junseo Bang, Youngjin Kim, Hyunwoo Son, Changhyun Kim, Junhyeok Jang, Yoonchan Jeong, and Byoungho Lee
    Nano Letters, 2024
  3. ACS Photonics
    BilayerNanoResonator.gif
    Strong Coupling Induced Bound States in the Continuum in a Hybrid Metal–Dielectric Bilayer Nanograting Resonator
    Hyunwoo Son, Taewon Choi, Kyuho Kim, Youngjin Kim, Junseo Bang, Sun-Je Kim, Byoungho Lee, and Yoonchan Jeong
    ACS Photonics, 2024