Zobrazeno 1 - 10
of 1 508
pro vyhledávání: '"Niu Wei"'
Autor:
Zhan, Zheng, Wu, Yushu, Gong, Yifan, Meng, Zichong, Kong, Zhenglun, Yang, Changdi, Yuan, Geng, Zhao, Pu, Niu, Wei, Wang, Yanzhi
The rapid progress in artificial intelligence-generated content (AIGC), especially with diffusion models, has significantly advanced development of high-quality video generation. However, current video diffusion models exhibit demanding computational
Externí odkaz:
http://arxiv.org/abs/2411.01171
Autor:
Zhan, Zheng, Kong, Zhenglun, Gong, Yifan, Wu, Yushu, Meng, Zichong, Zheng, Hangyu, Shen, Xuan, Ioannidis, Stratis, Niu, Wei, Zhao, Pu, Wang, Yanzhi
State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a new type of powerful vision foundation model. Inspired by the observatio
Externí odkaz:
http://arxiv.org/abs/2409.18962
Autor:
Jia, Wenqi, Liu, Youyuan, Hu, Zhewen, Wang, Jinzhen, Zhang, Boyuan, Niu, Wei, Huang, Junzhou, Kalafatis, Stavros, Jin, Sian, Yin, Miao
Large-scale scientific simulations generate massive datasets that pose significant challenges for storage and I/O. While traditional lossy compression techniques can improve performance, balancing compression ratio, data quality, and throughput remai
Externí odkaz:
http://arxiv.org/abs/2409.05785
Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN's overfitting properties to perform video resolution up
Externí odkaz:
http://arxiv.org/abs/2407.02813
Autor:
Luo, Zhongzhong, Yu, Zhihao, Lu, Xiangqian, Niu, Wei, Yu, Yao, Yao, Yu, Tian, Fuguo, Tan, Chee Leong, Sun, Huabin, Gao, Li, Qin, Wei, Xu, Yong, Zhao, Qiang, Song, Xiang-Xiang
Publikováno v:
Nano Lett. (2024)
Two-dimensional (2D) materials are promising candidates for spintronic applications. Maintaining their atomically smooth interfaces during integration of ferromagnetic (FM) electrodes is crucial since conventional metal deposition tends to induce def
Externí odkaz:
http://arxiv.org/abs/2405.06940
Autor:
Niu, Wei, Sanim, Md Musfiqur Rahman, Shu, Zhihao, Guan, Jiexiong, Shen, Xipeng, Yin, Miao, Agrawal, Gagan, Ren, Bin
This work is motivated by recent developments in Deep Neural Networks, particularly the Transformer architectures underlying applications such as ChatGPT, and the need for performing inference on mobile devices. Focusing on emerging transformers (spe
Externí odkaz:
http://arxiv.org/abs/2404.13528
The rapid expansion of computational capabilities and the ever-growing scale of modern HPC systems present formidable challenges in managing exascale scientific data. Faced with such vast datasets, traditional lossless compression techniques prove in
Externí odkaz:
http://arxiv.org/abs/2404.13470
Autor:
Liu, Jun, Wu, Chao, Yang, Changdi, Tang, Hao, Kong, Zhenglun, Yuan, Geng, Niu, Wei, Huang, Dong, Wang, Yanzhi
Large language models (LLMs) have become crucial for many generative downstream tasks, leading to an inevitable trend and significant challenge to deploy them efficiently on resource-constrained devices. Structured pruning is a widely used method to
Externí odkaz:
http://arxiv.org/abs/2403.10799
Autor:
Zhang, Xu, Zhu, Tongshuai, Zhang, Shuai, Chen, Zhongqiang, Song, Anke, Zhang, Chong, Gao, Rongzheng, Niu, Wei, Chen, Yequan, Fei, Fucong, Tai, Yilin, Li, Guoan, Ge, Binghui, Lou, Wenkai, Shen, Jie, Zhang, Haijun, Chang, Kai, Song, Fengqi, Zhang, Rong, Wang, Xuefeng
Publikováno v:
Nature Communications (2024)
Nonlinear transport is a unique functionality of noncentrosymmetric systems, which reflects profound physics, such as spin-orbit interaction, superconductivity and band geometry. However, it remains highly challenging to enhance the nonreciprocal tra
Externí odkaz:
http://arxiv.org/abs/2403.04515
Though many compilation and runtime systems have been developed for DNNs in recent years, the focus has largely been on static DNNs. Dynamic DNNs, where tensor shapes and sizes and even the set of operators used are dependent upon the input and/or ex
Externí odkaz:
http://arxiv.org/abs/2403.00176