1 code implementation • 4 Mar 2024 • XUDONG ZHU, Zhao Kang, Bei Hui
State-of-the-art DocRE methods use a graph structure to connect entities across the document to capture dependency syntax information.
no code implementations • 1 Jan 2024 • Shi Yin, Xinyang Pan, XUDONG ZHU, Tianyu Gao, Haochong Zhang, Feng Wu, Lixin He
Deep learning for predicting the electronic structure Hamiltonian of quantum systems necessitates satisfying the covariance laws, among which achieving SO(3)-equivariance without sacrificing the non-linear expressive capability of networks remains unsolved.
no code implementations • journal 2017 • XUDONG ZHU, Zhaocheng Wang, JIANFEI CAO
By introducing non-OMA (NOMA) into SM for DL-MU transmission, NOMA-based SM (NOMA-SM) is proposed to mitigate inter-user interference, while maintaining high spectral efficiency.