We repurpose geometric foundation model features as latent space for multi-view diffusion, achieving 4.4× faster training convergence and zero-shot geometry decoding.
Under Review, 2026
A visual builder for creating academic research project pages — drag-and-drop sections, multiple templates, LLM-powered paper extraction, and one-click GitHub deployment.
A training technique that supervises attention maps using geometric correspondence, reducing training iterations by half while achieving superior multi-view generation quality.
CVPR 2026
A method that learns condition-dependent source distributions for flow matching, enabling straighter transport paths and up to 3x faster convergence.
Under Review
A practical study on improving semantic segmentation for autonomous driving under limited data and compute, focusing on architecture choices, coordinate-aware convolutions, and optimizer/schedule tuning.
AIKU (Korea University AI Society) Internal Project
A novel framework that redefines motion guidance in video diffusion by extracting 'pseudo-flow' from 2D attention layers, enabling more interpretable and robust motion transfer.
IEIE 2025 Undergraduate Paper Competition (Excellence Award)
A benchmark dataset and evaluation protocol for object motion transfer, introducing improved metrics that better correlate with human perception.
ITC-CSCC (Oral)
Finetuned semantic map-conditioned LDMs with ControlNet for unsupervised and unpaired Synthetic-to-Real image translation.
AI profile picture generation service for Korea University festival — identity-preserving Stable Diffusion pipeline serving 2,000+ students.
Proposed faster and stable caption generation utilizing Gibbs sampling and Masked VLM for zero-shot image captioning.
Music recommendation service using VLM and LLM-based lyrics augmentation to match user preferences and context.