Sangkyung Kwak

5 papers · 2024–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

CVPR (1) ECCV (1) ICLR (1) IJCAI (1) NeurIPS (1)

Top co-authors

Jinwoo Shin (5) Kyungmin Lee (3) Sihyun Yu (2) Hyungwon Choi (2) Jongheon Jeong (2) Yisol Choi (2) Huiwon Jang (1) Saining Xie (1) Juho Lee (1) Kihyuk Sohn (1)

Research topics

Deep Learning (4) Models (4) Machine Learning (3) Artificial Intelligence (2) Computer Vision (2) Application Areas (2) Core Methods (2) Generation (2) Architectures (1) Core AI (1) Learning Paradigms (1) Techniques (1)

Keywords

diffusion model (3) text-to-image diffusion (2) image generation (2) virtual try-on (2) representation learning (2) spurious correlation (1) controllable generation (1) visual encoder (1) cross attention (1) self attention (1) model customization (1) human image generation (1) prompt fidelity (1) subject fidelity (1) garment extraction (1) garment image extraction (1) customization method (1) garment image (1) garment fidelity (1) zero-shot learning (1)

Papers

Controllable Human Image Generation with Personalized Multi-Garments CVPR 2025 Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think ICLR 2025 StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment IJCAI 2025 Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models NeurIPS 2024 Improving Diffusion Models for Authentic Virtual Try-on in the Wild ECCV 2024