8 citations · 27 across the 11 of their papers we have counts for
11 papers
AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
Yifan Liu, Wenkuan Zhao, Shanshan Zhong +4
Recent advancements in multimodal large language models (MLLMs) have garnered significant attention, offering a promising pathway toward artificial general intelligence (AGI). Amon…
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…
Exploring Compositional Visual Generation with Latent Classifier Guidance
Changhao Shi, Haomiao Ni, Kai Li +3
Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion m…
AttNS: Attention-Inspired Numerical Solving For Limited Data Scenarios
Zhongzhan Huang, Mingfu Liang, Shanshan Zhong +1
We propose the attention-inspired numerical solver (AttNS), a concise method that helps the generalization and robustness issues faced by the AI-Hybrid numerical solver in solving…
A Generic Shared Attention Mechanism for Various Backbone Neural Networks
Zhongzhan Huang, Senwei Liang, Mingfu Liang +1
The self-attention mechanism has emerged as a critical component for improving the performance of various backbone neural networks. However, current mainstream approaches individua…
The Lottery Ticket Hypothesis for Self-attention in Convolutional Neural Network
Zhongzhan Huang, Senwei Liang, Mingfu Liang +3
Recently many plug-and-play self-attention modules (SAMs) are proposed to enhance the model generalization by exploiting the internal information of deep convolutional neural netwo…
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…
Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch Noise
Senwei Liang, Zhongzhan Huang, Mingfu Liang +1
Batch Normalization (BN)(Ioffe and Szegedy 2015) normalizes the features of an input image via statistics of a batch of images and hence BN will bring the noise to the gradient of…
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…