SchoenbAt: Rethinking Attention with Polynomial basis

1 code implementation • 18 May 2025 • Yuhan Guo, Lizhong Ding, Yuwan Yang, Xuewei Guo

Kernelized attention extends the attention mechanism by modeling sequence correlations through kernel functions, making significant progresses in optimizing attention.

IRRGN: An Implicit Relational Reasoning Graph Network for Multi-turn Response Selection

1 code implementation • 1 Dec 2022 • Jingcheng Deng, Hengwei Dai, Xuewei Guo, Yuanchen Ju, Wei Peng

URR aims to implicitly extract dependencies between utterances, as well as utterances and options, and make reasoning with relational graph convolutional networks.

Relational Reasoning