#long-tail-distribution2 articles

2 articles

AIBullisharXiv – CS AI · 6h ago2

🧠

REMIND: Rethinking Medical High-Modality Learning under Missingness--A Long-Tailed Distribution Perspective

Researchers propose REMIND, a framework for medical multi-modal AI learning that addresses the challenge of missing data across multiple modalities. The solution uses a Mixture-of-Experts architecture to handle long-tail distributions of modality combinations and shows superior performance on real-world medical datasets.

AIBullisharXiv – CS AI · 6h ago0

🧠

Towards Principled Dataset Distillation: A Spectral Distribution Perspective

Researchers propose Class-Aware Spectral Distribution Matching (CSDM), a new dataset distillation method that addresses performance issues on imbalanced datasets. The technique achieves 14% improvement over existing methods on CIFAR-10-LT with enhanced stability on long-tailed data distributions.