Zobrazeno 1 - 10
of 4 557
pro vyhledávání: '"SHAO, Bin"'
The traditional image inpainting task aims to restore corrupted regions by referencing surrounding background and foreground. However, the object erasure task, which is in increasing demand, aims to erase objects and generate harmonious background. P
Externí odkaz:
http://arxiv.org/abs/2410.10207
Autor:
Wang, Yusong, Cheng, Chaoran, Li, Shaoning, Ren, Yuxuan, Shao, Bin, Liu, Ge, Heng, Pheng-Ann, Zheng, Nanning
Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems. To address this challenge, we intr
Externí odkaz:
http://arxiv.org/abs/2409.17622
Autor:
Ren, Jingjing, Li, Wenbo, Chen, Haoyu, Pei, Renjing, Shao, Bin, Guo, Yong, Peng, Long, Song, Fenglong, Zhu, Lei
Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture utilizing ca
Externí odkaz:
http://arxiv.org/abs/2407.02158
Autor:
Ju, Fusong, Wei, Xinran, Huang, Lin, Jenkins, Andrew J., Xia, Leo, Zhang, Jia, Zhu, Jianwei, Yang, Han, Shao, Bin, Dai, Peggy, Mayya, Ashwin, Hooshmand, Zahra, Efimovskaya, Alexandra, Baker, Nathan A., Troyer, Matthias, Liu, Hongbin
Density functional theory (DFT) has been a cornerstone in computational chemistry, physics, and materials science for decades, benefiting from advancements in computational power and theoretical methods. This paper introduces a novel, cloud-native ap
Externí odkaz:
http://arxiv.org/abs/2406.11185
Autor:
Wang, Zun, Liu, Chang, Zou, Nianlong, Zhang, He, Wei, Xinran, Huang, Lin, Wu, Lijun, Shao, Bin
In this study, we introduce a unified neural network architecture, the Deep Equilibrium Density Functional Theory Hamiltonian (DEQH) model, which incorporates Deep Equilibrium Models (DEQs) for predicting Density Functional Theory (DFT) Hamiltonians.
Externí odkaz:
http://arxiv.org/abs/2406.03794
In this paper, we develop SE3Set, an SE(3) equivariant hypergraph neural network architecture tailored for advanced molecular representation learning. Hypergraphs are not merely an extension of traditional graphs; they are pivotal for modeling high-o
Externí odkaz:
http://arxiv.org/abs/2405.16511
Molecular dynamics (MD) is a crucial technique for simulating biological systems, enabling the exploration of their dynamic nature and fostering an understanding of their functions and properties. To address exploration inefficiency, emerging enhance
Externí odkaz:
http://arxiv.org/abs/2405.00751
Autor:
Zhang, He, Liu, Chang, Wang, Zun, Wei, Xinran, Liu, Siyuan, Zheng, Nanning, Shao, Bin, Liu, Tie-Yan
Predicting the mean-field Hamiltonian matrix in density functional theory is a fundamental formulation to leverage machine learning for solving molecular science problems. Yet, its applicability is limited by insufficient labeled data for training. I
Externí odkaz:
http://arxiv.org/abs/2403.09560
Autor:
Zhang, He, Liu, Siyuan, You, Jiacheng, Liu, Chang, Zheng, Shuxin, Lu, Ziheng, Wang, Tong, Zheng, Nanning, Shao, Bin
Orbital-free density functional theory (OFDFT) is a quantum chemistry formulation that has a lower cost scaling than the prevailing Kohn-Sham DFT, which is increasingly desired for contemporary molecular research. However, its accuracy is limited by
Externí odkaz:
http://arxiv.org/abs/2309.16578
We investigate the orthogonality catastrophe and quantum speed limit in the Creutz model for dynamical quantum phase transitions. We demonstrate that exact zeros of the Loschmidt echo can exist in finite-size systems for specific discrete values. We
Externí odkaz:
http://arxiv.org/abs/2308.04686