5 papers
NormDirection: Restoring the Missing Query Norm in Vision Linear Attention
Weikang Meng, Yadan Luo, Liangyu Huo +4
Linear attention mitigates the quadratic complexity of softmax attention but suffers from a critical loss of expressiveness. We identify two primary causes: (1) The normalization o…
Latent-Condensed Transformer for Efficient Long Context Modeling
Zeng You, Yaofo Chen, Qiuwu Chen +5
Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention…
MirrorLA: Reflecting Feature Map for Vision Linear Attention
Weikang Meng, Liangyu Huo, Yadan Luo +3
Linear attention significantly reduces the computational complexity of Transformers from quadratic to linear, yet it consistently lags behind softmax-based attention in performance…
STILL: Selecting Tokens for Intra-Layer Hybrid Attention to Linearize LLMs
Weikang Meng, Liangyu Huo, Yadan Luo +4
Linearizing pretrained large language models (LLMs) primarily relies on intra-layer hybrid attention mechanisms to alleviate the quadratic complexity of standard softmax attention.…
Training-free Context-adaptive Attention for Efficient Long Context Modeling
Zeng You, Yaofo Chen, Shuhai Zhang +5
Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of natural language processing tasks. These capabilities stem primarily from the self-att…