Joonseok Lee

A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction

Equivariant Latent Alignment via Flow Matching under Group Symmetries

TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization

Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning

Towards Robust Benchmark of Object Hallucination on Multiple Images

Geometry-Aware Image Flow Matching

Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

Self-Guided Masked Autoencoder