2 papers
cs.LG2026
Spectral Gradient Surgery for Domain-Generalizable Dataset Distillation
Minyoung Oh, Najeong Chae, Jae-Young Sim
Dataset Distillation (DD) synthesizes a compact synthetic dataset that preserves the training utility of a full dataset. However, its standard formulation assumes that test data fo…
cs.CV2026
CLIP-RD: Relative Distillation for Efficient CLIP Knowledge Distillation
Jeannie Chung, Hanna Jang, Ingyeong Yang +2
CLIP aligns image and text embeddings via contrastive learning and demonstrates strong zero-shot generalization. Its large-scale architecture requires substantial computational and…