Yongmin Lee

MS student, KAIST

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

#108 · Yongmin Lee, Hye Won Chung

We propose CovMatch, a scalable dataset distillation method for image-text contrastive learning that aligns cross-covariance and feature distributions between real and synthetic data.