Publications

Jaeyo Shin*, Jiwook Kim*, Hyunjung Shim (2026). Representation Alignment for Just Image Transformers is not Easier than You Think. ArXiv.

Seonho Lee*, Jiho Choi*, Inha Kang, Jiwook Kim, Junsung Park, Hyunjung Shim (2025). 3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation. In EMNLP 2025 Findings.

Dohun Lee*, Hyeonho Jeong*, Jiwook Kim, Duygu Ceylan, Jong Chul Ye (2025). Improving Video Diffusion Transformer Training by Multi-Feature Fusion and Alignment from Self-Supervised Vision Encoders. ArXiv.

Jiwook Kim*, Seonho Lee*, Jaeyo Shin, Jiho Choi, Hyunjung Shim (2025). DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation. In ICLR 2025.

Jiwook Kim, Minhyeok Lee (2023). Class-Continuous Conditional Generative Neural Radiance Field. In BMVC 2023.

Jiwook Kim, Minhyeok Lee (2023). Portfolio Optimization using Predictive Auxiliary Classifier Generative Adversarial Networks. In EAAI.