3 papers
cs.LG2025
Data-Efficient Training by Evolved Sampling
Ziheng Cheng, Zhong Li, Jiang Bian
Data selection is designed to accelerate learning with preserved performance. To achieve this, a fundamental thought is to identify informative data samples with significant contri…
eess.IV2025
AURAD: Anatomy-Pathology Unified Radiology Synthesis with Progressive Representations
Shuhan Ding, Jingjing Fu, Yu Gu +6
Medical image synthesis has become an essential strategy for augmenting datasets and improving model generalization in data-scarce clinical settings. However, fine-grained and cont…
cs.LG2025
FlashMask: Efficient and Rich Mask Extension of FlashAttention
Guoxia Wang, Jinle Zeng, Xiyuan Xiao +7
The computational and memory demands of vanilla attention scale quadratically with the sequence length , posing significant challenges for processing long sequences in Transform…