Joonghyuk Shin
Scholar

Joonghyuk Shin

Google Scholar ID: -FvJw80AAAAJ
Seoul National University, CSE
Machine LearningComputer Vision
Citations & Impact
All-time
Citations
127
 
H-index
3
 
i10-index
3
 
Publications
5
 
Co-authors
2
list available
Resume (English only)
Academic Achievements
  • JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching (arXiv 2025): A unified framework for synchronized facial motion and speech generation using flow matching and MM-DiT
  • Exploring Multimodal Diffusion Transformers for Enhanced Prompt-based Image Editing (ICCV 2025): Systematic analysis of bidirectional attention in MM-DiT and a robust prompt-based editing method
  • InstantDrag: Improving Interactivity in Drag-based Image Editing (SIGGRAPH Asia 2024): Optimization-free pipeline for fast drag-based image editing
  • Fill-Up: Balancing Long-Tailed Data with Generative Models (arXiv 2023): Two-stage method using textual-inverted tokens for long-tailed recognition
  • StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis (TPAMI 2023): Comprehensive library reproducing 30+ GAN models with standardized benchmarks
  • Outstanding Poster Presentation Award, IPIU (2023, 2025)
  • Summa Cum Laude, POSTECH (2023)
  • National Science and Engineering Scholarship, Korea Student Aid Foundation (2021, 2022)
  • Best Graduation Project, POSTECH CSE (2022)
  • Silver Award, UNI-DTHON Datathon (2021)
  • Best Undergraduate Research Program, POSTECH (2020)