2 papers
cs.DC2026
FlashMLA-ETAP: Efficient Transpose Attention Pipeline for Accelerating MLA Inference on NVIDIA H20 GPUs
Pengcuo Dege, Qiuming Luo, Rui Mao +1
Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a…
cs.CV2026
Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition
Qiuming Luo, Tao Zeng, Feng Li +3
Zero-shot Handwritten Chinese Character Recognition (HCCR) aims to recognize unseen characters by leveraging radical-based semantic compositions. However, existing approaches often…