Junoh Kang

About

I am a Ph.D. candidate in Electrical and Computer Engineering at Seoul National University, advised by Prof. Bohyung Han ↗. My research focuses on generative modeling for financial markets, including limit-order-book simulation and path signatures, in collaboration with Prof. Kiseop Lee ↗. Previously, I worked on efficient sampling for diffusion models. I was a research intern at Adobe Research ↗ in 2024. I received my B.S. in Statistics and Mathematics from Seoul National University, summa cum laude.

Research Interests

  • Generative modeling for financial markets

    • Under review · 1st author — an LOB message generator whose messages are replayable by construction
    • NeurIPS 2026 · 1st author — a probabilistic reframing of truncated signature inversion that quantifies its inherent ambiguity
  • Efficient sampling for diffusion models

    • ICLR 2025 — a few-step diffusion sampler inspired by Richardson extrapolation
    • CVPR 2024 · 1st author — a training method for few-step diffusion sampling

News

Show older news (5)

Education

  • Seoul National University Mar 2022 – Exp. Feb 2028

    Ph.D. program in Electrical and Computer Engineering

    Advisor: Prof. Bohyung Han

  • Seoul National University Mar 2015 – Aug 2021

    B.S. in Statistics and Mathematics

    Summa Cum Laude, GPA 4.0/4.3

  • Seoul Science High School (SSHS) Mar 2012 – Feb 2015

Experience

Selected Publications

* equal contribution
  • ReLOBGen: Replayable Limit Order Book Message Generation

    Junoh Kang, Kiseop Lee, Bohyung Han

    Under review Project
  • Probabilistic Signature Inversion: Learning Conditional Distributions from Truncated Signatures

    Junoh Kang, Kiseop Lee, Bohyung Han

    NeurIPS 2026 Paper
  • Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions

    Jinyoung Choi, Junoh Kang, Bohyung Han

    ICLR 2025 Paper /Code
  • FIFO-Diffusion: Generating Infinite Videos from Text without Training

    Jihwan Kim*, Junoh Kang*, Jinyoung Choi, Bohyung Han

    NeurIPS 2024 · Gold medal, Samsung Humantech Paper Award Paper /Project /Code
  • Observation-Guided Diffusion Probabilistic Models

    Junoh Kang*, Jinyoung Choi*, Sungik Choi, Bohyung Han

    CVPR 2024 Paper /Code
Full publication list →

Honors

Academic Services

Reviewer

Conference: NeurIPS, AAAI, WACV, CVPR

Search