Building Reliable and Efficient Multimodal AI
I am a Ph.D. student in Electrical and Computer Engineering at Seoul National University, working with the Intelligent Computing Lab. My research focuses on multimodal language-vision systems, diffusion-based generation, and robust visual representation learning.
Publications
11
Latest Publication
2026
Latest News
Mar 2026
Research Focus
Multimodal Language-Vision Models
Understanding and reducing object hallucinations with uncertainty-aware token analysis.
Diffusion Model Efficiency
Improving speed and memory efficiency with adaptive sampling and lightweight optimization.
Text-to-Image Alignment
Studying token geometry and cross-attention behavior for stronger semantic binding.
Practical Robustness
Designing methods that remain effective under limited compute and real-world constraints.
Recent News
Mar 12, 2026
3 Papers accepted to CVPR 2026 (2 first-authored, 1 co-authored)! See you in Denver, Colorado!
Oct 02, 2025
Received BK21Four - SNU Fellowship of Research Excellence ($7,000).
Sep 25, 2025
Our paper "On Epistemic Uncertainty of Visual Tokens~" was accepted to NeurIPS 2025 (poster).
Aug 19, 2025
Released RALU: region-adaptive latent sampling for accelerated diffusion transformers.
May 01, 2025
Skrr was accepted to ICML 2025 (poster).
Apr 26, 2025
Harmonization for a black-box deep learning model was selected as Summa cum laude at ISMRM 2025.
Apr 01, 2025
Efficient Personalization of Quantized Diffusion Model without Backpropagation was accepted to EDGE@CVPR 2025.
Mar 29, 2025
Released TeeMo on geometric properties of text token embeddings for stronger semantic binding.
Feb 27, 2025
Efficient Personalization of Quantized Diffusion Model without Backpropagation was accepted to CVPR 2025 (poster).
Feb 01, 2025
Harmonization for a black-box deep learning model was accepted to ISMRM 2025 as an oral presentation.
