activity
20232025
most citedMultimodal Variational Auto-encoder based Audio-Visual Segmentation

2 citations · 4 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2024

You Only Scan Once: Efficient Multi-dimension Sequential Modeling with LightNet

Zhen Qin, Yuxin Mao, Xuyang Shen +4

Linear attention mechanisms have gained prominence in causal language models due to their linear computational complexity and enhanced speed. However, the inherent decay mechanism…