Zobrazeno 1 - 10
of 821
pro vyhledávání: '"Wang, Pengbo"'
Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs significantly restricts their practica
Externí odkaz:
http://arxiv.org/abs/2405.00338
Autor:
Wang, Yiqing, Liu, Xiaoyan, Yang, Hailong, Yang, Xinyu, Wang, Pengbo, Liu, Yi, Luan, Zhongzhi, Qian, Depei
As modern HPC computing platforms become increasingly heterogeneous, it is challenging for programmers to fully leverage the computation power of massive parallelism offered by such heterogeneity. Consequently, task-based runtime systems have been pr
Externí odkaz:
http://arxiv.org/abs/2404.03226
Sampling critical testing scenarios is an essential step in intelligence testing for Automated Vehicles (AVs). However, due to the lack of prior knowledge on the distribution of critical scenarios in sampling space, we can hardly efficiently find the
Externí odkaz:
http://arxiv.org/abs/2405.00696
Autor:
Wang, Siqi, Yang, Hailong, Wang, Xuezhu, Liu, Tongxuan, Wang, Pengbo, Liang, Xuning, Ma, Kejie, Feng, Tianyu, You, Xin, Bao, Yongjun, Liu, Yi, Luan, Zhongzhi, Qian, Depei
Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates tokens only
Externí odkaz:
http://arxiv.org/abs/2402.15678
This paper presents a Long Range (LoRa) physical-layer data aggregation system (LoRaPDA) that aggregates data (e.g., sum, average, min, max) directly in the physical layer. In particular, after coordinating a few nodes to transmit their data simultan
Externí odkaz:
http://arxiv.org/abs/2212.06582
Publikováno v:
陆军军医大学学报, Vol 46, Iss 7, Pp 651-660 (2024)
Objective To explore the impact of the sialic acid binding lectin-E (Siglec-E) on the inhibitory properties of parthenolide(PTL) against lipopolysaccharide (LPS)-induced M1 polarization of microglia(BV2). Methods ① Single cell sequencing data of Si
Externí odkaz:
https://doaj.org/article/40c8ad7ebc054f13b2c00432b9a57e4c
Publikováno v:
COMPEL -The international journal for computation and mathematics in electrical and electronic engineering, 2023, Vol. 42, Issue 6, pp. 1798-1811.
Autor:
Tang, Tao1 (AUTHOR) tangtao@buaa.edu.cn, Wang, Pengbo1 (AUTHOR) wangpb7966@buaa.edu.cn, Chen, Jie1 (AUTHOR), Yao, Huguang1 (AUTHOR), Ren, Ziheng1 (AUTHOR), Zhao, Peng1 (AUTHOR), Zeng, Hongcheng1 (AUTHOR)
Publikováno v:
Remote Sensing. Jul2024, Vol. 16 Issue 13, p2345. 24p.
Autor:
Yu, Hongjiu, Sun, Qiancheng, Hu, Jin, Xue, Xingyuan, Luo, Jixiang, He, Dailan, Li, Yilong, Wang, Pengbo, Wang, Yuanyuan, Dai, Yaxu, Wang, Yan, Qin, Hongwei
Learned image compression has achieved extraordinary rate-distortion performance in PSNR and MS-SSIM compared to traditional methods. However, it suffers from intensive computation, which is intolerable for real-world applications and leads to its li
Externí odkaz:
http://arxiv.org/abs/2207.14524
Autor:
Zhou, Changhui, Wang, Pengbo, Li, Jinhua, Zhang, Yan, Bai, Jing, Cui, Hanbo, Liu, Geying, Long, Mingce, Zhou, Baoxue
Publikováno v:
In Journal of Hazardous Materials 15 May 2024 470