Portrait of Yoojin Jang

Yoojin Jang

Hi all, I am an integrated M.S./Ph.D. student at UNIST, advised by Prof. Jaejun Yoo. My research interests include multimodal data generation models across video, audio, and text, as well as building robust dataset benchmarks.

Current focus

  • Video-to-audio generation
  • Multimodal benchmarks

News

Recent updates.

  1. 2026

    AVENUE: Audio-Video EditiNg Understanding and Evaluation

    Hayeon Kim*, Yoojin Jang*, Jaejun Yoo ( equal contribution)

    Accepted, Learning to Listen: ICML 2026 Workshop on Machine Learning for Audio

  2. 2026

    Rethinking Video-and-Text-to-Audio Generation through Multimodal Coverage

    Sangyeop Yeo, Yoojin Jang, Saad Mourafik, Arda Senocak, Jaejun Yoo

    Accepted, Sight and Sound 2026, CVPR Workshop

Publications

International conferences.

  1. B-RIGHT: Benchmark Re-evaluation for Integrity in Generalized Human-Object Interaction Testing

    Yoojin Jang*, Junsu Kim *, Hayeon Kim, Eun-ki Lee, Eun-sol Kim , Seungryul Baek , Jaejun Yoo ( equal contribution)

    BMVC · 2025

    A rebuilt HOI benchmark — equal instances per class, plus a balanced zero-shot split that re-ranks the field.

    arXiv Code

    • benchmark
    • HOI
    • evaluation

  2. Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation

    Sangyeop Yeo , Yoojin Jang, Jaejun Yoo

    ECCV · 2024

    Two methods — DiME and NICKEL — that compress StyleGAN2 by 99% while keeping its image quality intact.

    arXiv Code Project page

    • GAN
    • knowledge-distillation
    • efficiency

  3. TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

    Pum Jun Kim, Yoojin Jang, Jisu Kim , Jaejun Yoo

    NeurIPS · 2023

    Topological precision and recall that fix what FID and P&R quietly overlook — the support estimate itself.

    arXiv Code Project page

    • evaluation
    • generative-models
    • topological data analysis

Education

Academic background.

Integrated M.S. and Ph.D., AI Graduate School

UNIST · Ulsan, South Korea

Advisor: Prof. Jaejun Yoo

Sep 2021 — Now

B.S., Department of Software Convergence

Seoul Women's University · Seoul, South Korea

Advisors: Prof. Helen Hong, Prof. Jun Hwang

Mar 2016 — Aug 2021

Before my journey