3 papers
cs.LG2026
BAPS: A Fine-Grained Low-Precision Scheme for Softmax in Attention via Block-Aware Precision reScaling
Zisheng Ye, Xiaoyu He, Maoyuan Song +10
As the performance gains from accelerating quantized matrix multiplication plateau, the softmax operation becomes the critical bottleneck in Transformer inference. This bottleneck…
cs.LG2026
A Provable Expressiveness Hierarchy in Hybrid Linear-Full Attention
Xiaowei Ye, Xiaoyu He, Chao Liao +2
Transformers serve as the foundation of most modern large language models. To mitigate the quadratic complexity of standard full attention, various efficient attention mechanisms,…
cs.CL2024
Cultural Adaptation of Menus: A Fine-Grained Approach
Zhonghe Zhang, Xiaoyu He, Vivek Iyer +1
Machine Translation of Culture-Specific Items (CSIs) poses significant challenges. Recent work on CSI translation has shown some success using Large Language Models (LLMs) to adapt…