2 papers
cs.LG2025
A Unified Geometric Field Theory Framework for Transformers: From Manifold Embeddings to Kernel Modulation
Xianshuai Shi, Jianfeng Zhu, Leibo Liu
The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However…
cs.NE2025
Gate-level boolean evolutionary geometric attention neural networks
Xianshuai Shi, Jianfeng Zhu, Leibo Liu
This paper presents a gate-level Boolean evolutionary geometric attention neural network that models images as Boolean fields governed by logic gates. Each pixel is a Boolean varia…