Zobrazeno 1 - 10
of 16 722
pro vyhledávání: '"JIANG Bo"'
Adapter-based tuning methods have shown significant potential in transferring knowledge from pre-trained Vision-Language Models to the downstream tasks. However, after reviewing existing adapters, we find they generally fail to fully explore the inte
Externí odkaz:
http://arxiv.org/abs/2410.07854
Although Large Language Models (LLMs) have achieved remarkable performance in numerous downstream tasks, their ubiquity has raised two significant concerns. One is that LLMs can hallucinate by generating content that contradicts relevant contextual i
Externí odkaz:
http://arxiv.org/abs/2410.03026
In this paper, we establish for the first time the oracle complexity of a Riemannian inexact augmented Lagrangian (RiAL) method with the classical dual update for solving a class of Riemannian nonsmooth composite problems. By using the Riemannian gra
Externí odkaz:
http://arxiv.org/abs/2410.00482
Autor:
Wang, Xiao, Wang, Fuling, Li, Yuehang, Ma, Qingchuan, Wang, Shiao, Jiang, Bo, Li, Chuanfu, Tang, Jin
X-ray image-based medical report generation (MRG) is a pivotal area in artificial intelligence which can significantly reduce diagnostic burdens and patient wait times. Despite significant progress, we believe that the task has reached a bottleneck d
Externí odkaz:
http://arxiv.org/abs/2410.00379
Recently, there has been growing interest in minimax problems on Riemannian manifolds due to their wide applications in machine learning and signal processing. Although many algorithms have been developed for minimax problems in the Euclidean setting
Externí odkaz:
http://arxiv.org/abs/2409.19588
Camera-LiDAR fusion models significantly enhance perception performance in autonomous driving. The fusion mechanism leverages the strengths of each modality while minimizing their weaknesses. Moreover, in practice, camera-LiDAR fusion models utilize
Externí odkaz:
http://arxiv.org/abs/2409.17728
Autor:
Liu, Wentao, Pan, Qianjun, Zhang, Yi, Liu, Zhuo, Wu, Ji, Zhou, Jie, Zhou, Aimin, Chen, Qin, Jiang, Bo, He, Liang
Large language models (LLMs) have obtained promising results in mathematical reasoning, which is a foundational skill for human intelligence. Most previous studies focus on improving and measuring the performance of LLMs based on textual math reasoni
Externí odkaz:
http://arxiv.org/abs/2409.02834
The Integrated Process Planning and Scheduling (IPPS) problem combines process route planning and shop scheduling to achieve high efficiency in manufacturing and maximize resource utilization, which is crucial for modern manufacturing systems. Tradit
Externí odkaz:
http://arxiv.org/abs/2409.00968
Autor:
Yao, Zhu-Heng, Yang, Sen, Guo, Wei-Jian, Chen, Yong-Jie, Songsheng, Yu-Yang, Bao, Dong-Wei, Jiang, Bo-Wei, Wang, Yi-Lin, Zhang, Hao, Hu, Chen, Li, Yan-Rong, Du, Pu, Xiao, Ming, Bai, Jin-Ming, Ho, Luis C., Brotherton, Michael S., Aceituno, Jesús, Winkler, Hartmut, Wang, Jian-Min
Over the past three decades, multiple reverberation mapping (RM) campaigns conducted for the quasar PG 2130+099 have exhibited inconsistent findings with time delays ranging from $\sim$10 to $\sim$200 days. To achieve a comprehensive understanding of
Externí odkaz:
http://arxiv.org/abs/2408.17407
Autor:
Cui, Susu, Han, Xueying, Han, Dongqi, Wang, Zhiliang, Wang, Weihang, Li, Yun, Jiang, Bo, Liu, Baoxu, Lu, Zhigang
Encrypted traffic classification plays a critical role in network security and management. Currently, mining deep patterns from side-channel contents and plaintext fields through neural networks is a major solution. However, existing methods have two
Externí odkaz:
http://arxiv.org/abs/2408.14122