Zobrazeno 1 - 10
of 3 719
pro vyhledávání: '"TANG, Peng"'
Autor:
Liu, Jiacheng, Tang, Peng, Wang, Wenfeng, Ren, Yuhang, Hou, Xiaofeng, Heng, Pheng-Ann, Guo, Minyi, Li, Chao
The emergence of large-scale Mixture of Experts (MoE) models has marked a significant advancement in artificial intelligence, offering enhanced model capacity and computational efficiency through conditional computation. However, the deployment and i
Externí odkaz:
http://arxiv.org/abs/2412.14219
Autor:
Tang, Peng, Liu, Jiacheng, Hou, Xiaofeng, Pu, Yifei, Wang, Jing, Heng, Pheng-Ann, Li, Chao, Guo, Minyi
The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge dev
Externí odkaz:
http://arxiv.org/abs/2411.01433
Autor:
Tang, Peng, Li, Xin, Chen, Yuxin, Qiu, Weidong, Mei, Haochen, Holmes, Allison, Li, Fenghua, Li, Shujun
Machine learning based classifiers that take a privacy policy as the input and predict relevant concepts are useful in different applications such as (semi-)automated compliance analysis against requirements of the EU GDPR. In all past studies, such
Externí odkaz:
http://arxiv.org/abs/2410.04754
Autor:
Kim, Sungnyun, Liao, Haofu, Appalaraju, Srikar, Tang, Peng, Tu, Zhuowen, Satzoda, Ravi Kumar, Manmatha, R., Mahadevan, Vijay, Soatto, Stefano
Visual document understanding (VDU) is a challenging task that involves understanding documents across various modalities (text and image) and layouts (forms, tables, etc.). This study aims to enhance generalizability of small VDU models by distillin
Externí odkaz:
http://arxiv.org/abs/2410.03061
The Dynamic Communication Network (DCN) describes the interactions over time among various communication nodes, and it is widely used in Big-data applications as a data source. As the number of communication nodes increases and temporal slots accumul
Externí odkaz:
http://arxiv.org/abs/2408.16573
Autor:
Yuan, Peng, Tang, Peng
Graph Neural Networks (GNNs) have emerged as powerful tools for analyzing and learning representations from graph-structured data. A crucial prerequisite for the outstanding performance of GNNs is the availability of complete graph information, i.e.,
Externí odkaz:
http://arxiv.org/abs/2408.04845
Autor:
Zhang, Wei, Tang, Peng
Accurate traffic Flow Prediction can assist in traffic management, route planning, and congestion mitigation, which holds significant importance in enhancing the efficiency and reliability of intelligent transportation systems (ITS). However, existin
Externí odkaz:
http://arxiv.org/abs/2408.04232
Publikováno v:
Lecture Notes in Computer Science 14897 (2024) 404-423
Textual passwords are still the most widely used user authentication mechanism. Due to the close connections between textual passwords and natural languages, advanced technologies in natural language processing (NLP) and machine learning (ML) could b
Externí odkaz:
http://arxiv.org/abs/2407.14145
Autor:
Tang, Peng, Lasser, Tobias
Existing multi-modal approaches primarily focus on enhancing multi-label skin lesion classification performance through advanced fusion modules, often neglecting the associated rise in parameters. In clinical settings, both clinical and dermoscopy im
Externí odkaz:
http://arxiv.org/abs/2407.09999
Autor:
Tang, Peng, Lasser, Tobias
In this study, we introduce a multi-modal approach that efficiently integrates multi-scale clinical and dermoscopy features within a single network, thereby substantially reducing model parameters. The proposed method includes three novel fusion sche
Externí odkaz:
http://arxiv.org/abs/2403.19203