Junha Hyung
Scholar

Junha Hyung

Google Scholar ID: DsaV5aQAAAAJ
PhD candidate, KAIST
Computer vision
Citations & Impact
All-time
Citations
99
 
H-index
5
 
i10-index
4
 
Publications
13
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • ACG: Action Coherence Guidance for Flow-based VLA models (under review)
  • Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs, EMNLP 2025
  • Temporal In-Context Fine-Tuning for Versatile Control of Video Diffusion Models, arXiv preprint, equal contribution
  • Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling, CVPR 2025, equal contribution
  • SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel-based Head Avatars, ICLR 2025, equal contribution
  • Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting, NeurIPS 2024
  • SelfSwapper: Self-Supervised Face Swapping via Shape Agnostic Masked AutoEncoder, ECCV 2024, equal contribution
  • Local 3D Editing via 3D Distillation of CLIP Knowledge, CVPR 2023
  • MagiCapture: High-Resolution Multi-Concept Portrait Customization, AAAI 2024, equal contribution
  • FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields
Research Experience
  • AI Research Intern, Game Intelligence Team, Microsoft Research, Jun. 2025 – Sep. 2025
  • AI Research Intern, Digital Human Team, NVIDIA, Jun. 2024 – Dec. 2024
  • AI Research Intern, Neural 3D Team, Naver Cloud, Feb. 2024 – Jun. 2024
  • AI Research Intern, Vision Intelligence Team, Kakao Enterprise, Jul. 2022 – Dec. 2022
  • AI Research Intern, Mindslab, Mar. 2021 – Aug. 2021
  • AI Fellowship, SKT, Jun. 2019 – Jun. 2020
  • AI Research Intern, Recommendation Systems Team, KAKAO, Sep. 2018 – Feb. 2019