Inyoung Jung

Inyoung Jung

M.S student at Sungkyunkwan Univ.

I am an M.S. graduate of SKKU (Sungkyunkwan University), South Korea, advised by Prof. Sungeun Hong in the Artificial Intelligence and Media Lab (AIM Lab). My research focuses on building robust and adaptive AI through multimodal learning and test-time adaptation. I have proposed novel frameworks for semantic segmentation and classification under domain shifts, leveraging class-wise alignment and adaptive thresholding. Recently, I introduced a question-aware temporal reasoning model for audio-visual question answering, which integrates Gaussian experts and modality interaction. My recent work expands into audio-visual reasoning and zero-shot test-time adaptation via prompt-based modality fusion.

🔥 News

  • 2025.09:  🎉🎉 Winner of the 2025 Sungkyunkwan University President’s List.
  • 2025.04:  🎉🎉 Question-Aware Gaussian Experts for Audio-Visual Question Answering was selected as highlight at CVPR 2025!
  • 2025.02:  🎉🎉 Question-Aware Gaussian Experts for Audio-Visual Question Answering is accpeted at CVPR 2025!
  • 2025.02:  🎉🎉 Winner of the Honorable Mention for Outstanding Paper Award at IPIU 2025.

📝 Publications

Equal contribution are denoted by *

  • Instance-Aware Test-Time Segmentation for Continual Domain Shifts, 2025
    Seunghwan Lee*, Inyoung Jung*, Hojoon Lee, Eunil Park, and Sungeun Hong
    [arXiv]

  • Question-Aware Gaussian Experts for Audio-Visual Question Answering, CVPR 2025 Highlight (Accept. rate 2.98%)
    Hongyeob Kim*, Inyoung Jung*, Dayoon Suh, Youjia Zhang, Sangmin Lee, and Sungeun Hong
    [project page] [paper] [arXiv] [code]

  • Prototypical Class-wise Test-Time Adaptation, Pattern Recognition Letters 2025
    Hojoon Lee, Seunghwan Lee, Inyoung Jung, and Sungeun Hong
    [DOI] [paper]

📄 Patents

  • System and Method for Question-Aware Audio-Visual Question Answering, KR-Application No. 10-2025-0176475, 2025.11 (SKKU).
  • Apparatus and Method for Generating an Image Learning Model, KR-Application No. 10-2024-0168645, 2024.11 (SKKU).

💡 Projects

  • 2025.08 - 2025.11: Development of a Logistics Volume Forecasting Model for Hub-to-Sub Routes Based on Time-Series Data, CJ Logistics-TES LAB (AI Development Team)
  • 2024.09 - 2025.08: Zero-Shot Question-Answering Framework with Adaptive Audio-Visual Fusion Prompts, M.S. Students Fellowship by National Research Foundation of Korea (NRF)
  • 2024.03 - 2025.05: RGB-X Path Networks for Multi-modal Multi-task Learning, by National Research Foundation of Korea (NRF)
  • 2024.03 - 2026.02: Metaverse Convergence Graduate School, by Institute for Information & Communications Technology Planning & Evaluation (IITP)
  • 2023.08 - 2023.12: Robust Deep Semantic Segmentation Model for Continual Domain Shifts, Capstone Design in Information and Communication Engineering by Inha University

🎖 Honors and Awards

  • 2025.09: Winner of the President’s List, Sungkyunkwan University 2025.
  • 2025.02: Honorable Mention for Outstanding Paper Award, IPIU 2025.
  • 2023.12: Excellence Award, Capstone Design for Information and Communication Engineering by Inha University.

📖 Educations

  • 2024.03 - 2026.02: Sungkyunkwan University, M.S. Department of Immersive Media Engineering.
  • 2021.03 - 2024.02: Inha University, Bachelor of Engineering, Department of Information and Communication Engineering.

💼 Experience