5 papers
Understanding and Improving Length Generalization in Hierarchical Sparse Attention Models
Jiaqi Leng, Xiang Hu, Junxiong Wang +3
Effectively processing long contexts is a critical challenge for language models. While standard Transformers are limited by quadratic complexity and poor length extrapolation, alt…
Flash Multi-Head Feed-Forward Network
Minshen Zhang, Xiang Hu, Jianguo Li +2
We explore Multi-Head FFN (MH-FFN) as a replacement of FFN in the Transformer architecture, motivated by the structural similarity between single-head attention and FFN. While mult…
Every Token Counts: Generalizing 16M Ultra-Long Context in Large Language Models
Xiang Hu, Zhanchao Zhou, Ruiqi Liang +3
This work explores the challenge of building ``Machines that Can Remember'', framing long-term memory as the problem of efficient ultra-long context modeling. We argue that this re…
Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access
Xiang Hu, Jiaqi Leng, Jun Zhao +2
A key advantage of Recurrent Neural Networks (RNNs) over Transformers is their linear computational and space complexity enables faster training and inference for long sequences. H…
Efficient Length-Generalizable Attention via Causal Retrieval for Long-Context Language Modeling
Xiang Hu, Zhihao Teng, Jun Zhao +2
Despite the success of Transformers, handling long contexts remains challenging due to the limited length generalization and quadratic complexity of self-attention. Thus Transforme…