Jihwan Kim

I am a first-year Master’s student in the Interdisciplinary Program in Artificial Intelligence 🧠 at Seoul National University, advised by Prof. Bohyung Han.

Before that, I completed my undergraduate studies in Department of Electrical and Computer Engineering ⚡ at SNU, where I also conducted research at CVLab on video generation using diffusion models. I co-authored a paper accepted to NeurIPS 2024 and worked with the SK Telecom Media Gen AI team 🎬 through their AI Fellowship, focusing on text-based video generation.

My research interests include autoregressive diffusion models, memory-augmented video generation, and vision-language models 🤖.

I’m driven to create AI that can see, remember, and imagine — pushing the boundaries of intelligent media.

Education

• M.S. in Interdisciplinary Program in Artificial Intelligence, Seoul National University, Sep.2024 - Present
• B.S. in Electrical & Computer Engineering, Seoul National University, Mar.2019 - Feb.2024

Publications

FIFO-Diffusion: Generating Infinite Videos from Text without Training
Jihwan Kim*, Junoh Kang*, Jinyoung Choi, Bohyung Han [Project page] [arXiv] [Code]

Experience

• Talent Internship Program, Samsung Electronics Co., Ltd. (Jul. 2020 - Aug. 2020)
  • Samsung Electronics Co., LTD.
  • Analog Design Team, System LSI.
    • Analog Circuit Design
    • Analog-to-Digital Converter (ADC)
• AI Research Engineer, Dalpha Inc (Jun. 2023 - Aug. 2023)
  • Dalpha Inc.
    • Virtual Try On
    • Short-form Video Generation
    • Avatar Generation
    • Real-time Facial Emotion Recognition in a Crowd
• Research Grant from fal.ai (Jun. 2023 - Aug. 2023)
  • fal.ai
    • Open-source projects
    • SV3D training
    • SVD Motion-LoRA
• Undergraduate Researcher (Jan. 2023 - Aug. 2024)
  • CVLAB, SNU
  • Supervisor: Bohyung Han
    • Long Video Generation via Diffusion Models
    • Text driven Image-to-Video Generation
    • Novel View Synthesis via Diffusion Models
• SKT AI Fellowship (May. 2024 - Nov. 2024)
  • Working with GST Media Gen AI team
    • Dynamic Layout Generation for Advertisement
    • Image/Video Background Generation

Honors and Awards

• Gold Award (1st prize in Signal Processing), 31th Samsung Humantech Paper Award - Jan. 2025
  • Awarded $15,000
• 1st Place, SK Telecom AI fellowship - Nov. 2024
  • Won first place among 16 teams in the fellowship research competition
  • Awarded $2,500.
• Graduated Summa Cum Laude, Seoul National University - Aug, 2024
  • Graduated Summa Cum Laude from SNU
• Specialized Semiconductor Program Scholarship, Grade A - Sep. 2023
  • Received a 10000$ grant from the SNU Specialized Semiconductor Program