45 citations · 68 across the 8 of their papers we have counts for
8 papers
A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and Human Brain Networks
Silin Chen, Yuzhong Chen, Caiwei Wang +9
Whether artificial neural networks organize information comparably to the human brain remains unclear. Prior brain--AI alignment studies are constrained by specific inputs and task…
Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT
Zhenxiang Xiao, Yuzhong Chen, Lu Zhang +14
Prompts have been proven to play a crucial role in large language models, and in recent years, vision models have also been using prompts to improve scalability for multiple downst…
When Brain-inspired AI Meets AGI
Lin Zhao, Lu Zhang, Zihao Wu +11
Artificial General Intelligence (AGI) has been a long-standing goal of humanity, with the aim of creating machines capable of performing any intellectual task that humans can do. T…
Mask-guided BERT for Few Shot Text Classification
Wenxiong Liao, Zhengliang Liu, Haixing Dai +11
Transformer-based language models have achieved significant success in various domains. However, the data-intensive nature of the transformer architecture requires much labeled dat…
Rectify ViT Shortcut Learning by Visual Saliency
Chong Ma, Lin Zhao, Yuzhong Chen +7
Shortcut learning is common but harmful to deep learning models, leading to degenerated feature representations and consequently jeopardizing the model's generalizability and inter…
Eye-gaze-guided Vision Transformer for Rectifying Shortcut Learning
Chong Ma, Lin Zhao, Yuzhong Chen +15
Learning harmful shortcuts such as spurious correlations and biases prevents deep neural networks from learning the meaningful and useful representations, thus jeopardizing the gen…
A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers
Yuzhong Chen, Yu Du, Zhenxiang Xiao +8
Vision transformer (ViT) and its variants have achieved remarkable successes in various visual tasks. The key characteristic of these ViT models is to adopt different aggregation s…
Mask-guided Vision Transformer (MG-ViT) for Few-Shot Learning
Yuzhong Chen, Zhenxiang Xiao, Lin Zhao +10
Learning with little data is challenging but often inevitable in various application scenarios where the labeled data is limited and costly. Recently, few-shot learning (FSL) gaine…