3 citations · 3 across the 5 of their papers we have counts for
5 papers · 1 filter
Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
Shiyu Zhao, Zhenting Wang, Felix Juefei-Xu +7
Prevailing Multimodal Large Language Models (MLLMs) encode the input image(s) as vision tokens and feed them into the language backbone, similar to how Large Language Models (LLMs)…
Understanding Self-attention Mechanism via Dynamical System Perspective
Zhongzhan Huang, Mingfu Liang, Jinghui Qin +2
The self-attention mechanism (SAM) is widely used in various fields of artificial intelligence and has successfully boosted the performance of different models. However, current ex…
Blending Pruning Criteria for Convolutional Neural Networks
Wei He, Zhongzhan Huang, Mingfu Liang +2
The advancement of convolutional neural networks (CNNs) on various vision applications has attracted lots of attention. Yet the majority of CNNs are unable to satisfy the strict re…
Efficient Attention Network: Accelerate Attention by Searching Where to Plug
Zhongzhan Huang, Senwei Liang, Mingfu Liang +2
Recently, many plug-and-play self-attention modules are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural networks (C…
DIANet: Dense-and-Implicit Attention Network
Zhongzhan Huang, Senwei Liang, Mingfu Liang +1
Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them…