Zobrazeno 1 - 10
of 24 507
pro vyhledávání: '"WEI, Cheng"'
Recent advancements in learned 3D representations have enabled significant progress in solving complex robotic manipulation tasks, particularly for rigid-body objects. However, manipulating granular materials such as beans, nuts, and rice, remains ch
Externí odkaz:
http://arxiv.org/abs/2410.09740
Autor:
Huang, Guantian, Li, Beibei, Fan, Xiaobing, Chatterjee, Aritrick, Wei, Cheng, Qi, Shouliang, Qian, Wei, He, Dianning
Accurate segmentation of various regions within the prostate is pivotal for diagnosing and treating prostate-related diseases. However, the scarcity of labeled data, particularly in specialized medical fields like prostate imaging, poses a significan
Externí odkaz:
http://arxiv.org/abs/2409.13371
Audio-visual pre-trained models have gained substantial attention recently and demonstrated superior performance on various audio-visual tasks. This study investigates whether pre-trained audio-visual models demonstrate non-arbitrary associations bet
Externí odkaz:
http://arxiv.org/abs/2409.12306
Autor:
Huang, Ning-Chi, Chang, Chi-Chih, Lin, Wei-Cheng, Taka, Endri, Marculescu, Diana, Wu, Kai-Chiang
$N{:}M$ sparsity is an emerging model compression method supported by more and more accelerators to speed up sparse matrix multiplication in deep neural networks. Most existing $N{:}M$ sparsity methods compress neural networks with a uniform setting
Externí odkaz:
http://arxiv.org/abs/2409.09708
Autor:
Chang, Kai-Wei, Wu, Haibin, Wang, Yu-Kai, Wu, Yuan-Kuei, Shen, Hua, Tseng, Wei-Cheng, Kang, Iu-thing, Li, Shang-Wen, Lee, Hung-yi
Publikováno v:
in IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 32, pp. 3730-3744, 2024
Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency in both sto
Externí odkaz:
http://arxiv.org/abs/2408.13040
HiMA: Hierarchical Quantum Microarchitecture for Qubit-Scaling and Quantum Process-Level Parallelism
Autor:
Zhou, Qi, Mei, Zi-Hao, Shi, Han-Qing, Guo, Liang-Liang, Yang, Xiao-Yan, Wang, Yun-Jie, Xu, Xiao-Fan, Xue, Cheng, Kong, Wei-Cheng, Wang, Jun-Chao, Wu, Yu-Chun, Chen, Zhao-Yun, Guo, Guo-Ping
Quantum computing holds immense potential for addressing a myriad of intricate challenges, which is significantly amplified when scaled to thousands of qubits. However, a major challenge lies in developing an efficient and scalable quantum control sy
Externí odkaz:
http://arxiv.org/abs/2408.11311
Recently, point clouds have been widely used in computer vision, whereas their collection is time-consuming and expensive. As such, point cloud datasets are the valuable intellectual property of their owners and deserve protection. To detect and prev
Externí odkaz:
http://arxiv.org/abs/2408.05500
Autor:
Chang, Chi-Chih, Lin, Wei-Cheng, Lin, Chien-Yu, Chen, Chong-Yan, Hu, Yu-Fang, Wang, Pei-Shuo, Huang, Ning-Chi, Ceze, Luis, Wu, Kai-Chiang
KV-Cache compression methods generally sample a KV-Cache of effectual tokens or quantize it into lower bits. However, these methods cannot exploit the redundancy of the hidden dimension of KV tensors. This paper investigates a unique hidden dimension
Externí odkaz:
http://arxiv.org/abs/2407.21118
Autor:
Zhang, Sheng, Duan, Peng, Wang, Yun-Jie, Wang, Tian-Le, Wang, Peng, Zhao, Ren-Ze, Yang, Xiao-Yan, Zhao, Ze-An, Guo, Liang-Liang, Chen, Yong, Zhang, Hai-Feng, Du, Lei, Tao, Hao-Ran, Li, Zhi-Fei, Wu, Yuan, Jia, Zhi-Long, Kong, Wei-Cheng, Chen, Zhao-Yun, Wu, Yu-Chun, Guo, Guo-Ping
In the NISQ era, achieving large-scale quantum computing demands compact circuits to mitigate decoherence and gate error accumulation. Quantum operations with diverse degrees of freedom hold promise for circuit compression, but conventional approache
Externí odkaz:
http://arxiv.org/abs/2407.06687
Autor:
Chen, Zhao-Yun, Ma, Teng-Yang, Ye, Chuang-Chao, Xu, Liang, Tan, Ming-Yang, Zhuang, Xi-Ning, Xu, Xiao-Fan, Wang, Yun-Jie, Sun, Tai-Ping, Chen, Yong, Du, Lei, Guo, Liang-Liang, Zhang, Hai-Feng, Tao, Hao-Ran, Wang, Tian-Le, Yang, Xiao-Yan, Zhao, Ze-An, Wang, Peng, Zhang, Sheng, Zhang, Chi, Zhao, Ren-Ze, Jia, Zhi-Long, Kong, Wei-Cheng, Dou, Meng-Han, Wang, Jun-Chao, Liu, Huan-Yu, Xue, Cheng, Zhang, Peng-Jun-Yi, Huang, Sheng-Hong, Duan, Peng, Wu, Yu-Chun, Guo, Guo-Ping
Quantum computational fluid dynamics (QCFD) offers a promising alternative to classical computational fluid dynamics (CFD) by leveraging quantum algorithms for higher efficiency. This paper introduces a comprehensive QCFD method, including an iterati
Externí odkaz:
http://arxiv.org/abs/2406.06063