Scholar
Sangeek Hyun
Google Scholar ID: xbaJDBwAAAAJ
Sungkyunkwan University
Citations & Impact
Citations
575
H-index
8
i10-index
7
Publications
15
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Scalable GANs with Transformers (Arxiv, 2025)
- Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation (ICCV, 2025)
- AESOP: Auto-Encoded Supervision for Perceptual Image Super-Resolution (CVPR, 2025)
- GSGAN: Adversarial Learning for Hierarchical Generation of 3D Gaussian Splats (NeurIPS, 2024) - Winner of Qualcomm Innovation Fellowship Korea 2024 (QIFK 2024)
- Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer (CVPR, 2024) - Highlight
- Diversity-aware Channel Pruning for StyleGAN Compression (CVPR, 2024)
- Task-disruptive Background Suppression for Few-Shot Segmentation (AAAI, 2024)
- Correlation-guided Query-Dependency Calibration in Video Representation Learning for Temporal Grounding (Arxiv, 2023)
- Frequency-based motion representation for video generative adversarial networks (TIP, 2023)
- Disentangled Representation Learning for Unsupervised Neural Quantization (CVPR, 2023)
Research Experience
- Recent research interest has been in 3D generative models using Generative Adversarial Networks and gaussian splatting. Also interested in various generation tasks using large-scale diffusion models.
Education
- Ph.D. candidate in the Visual Computing Lab (VCLab) at Sungkyunkwan University, supervised by Prof. Jae-Pil Heo. Received Master's and Bachelor's degrees from Sungkyunkwan University.
Background
- Research interests include various tasks in machine learning and computer vision, with a particular focus on generative models and video understanding.
Miscellany
- Contact: Email, Google Scholar, Github, LinkedIn
