Zobrazeno 1 - 10
of 573
pro vyhledávání: '"Wen Yonggang"'
Recent advancements in multimodal fusion have witnessed the remarkable success of vision-language (VL) models, which excel in various multimodal applications such as image captioning and visual question answering. However, building VL models requires
Externí odkaz:
http://arxiv.org/abs/2410.17779
Autor:
Liu, Yinqiu, Du, Hongyang, Niyato, Dusit, Kang, Jiawen, Xiong, Zehui, Wen, Yonggang, Kim, Dong In
Generative AI (GenAI), exemplified by Large Language Models (LLMs) such as OpenAI's ChatGPT, is revolutionizing various fields. Central to this transformation is Data Center Networking (DCN), which not only provides the computational power necessary
Externí odkaz:
http://arxiv.org/abs/2409.09343
Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias pr
Externí odkaz:
http://arxiv.org/abs/2409.05620
Autor:
Duan, Jiangfei, Zhang, Shuo, Wang, Zerui, Jiang, Lijuan, Qu, Wenwen, Hu, Qinghao, Wang, Guoteng, Weng, Qizhen, Yan, Hang, Zhang, Xingcheng, Qiu, Xipeng, Lin, Dahua, Wen, Yonggang, Jin, Xin, Zhang, Tianwei, Sun, Peng
Large Language Models (LLMs) like GPT and LLaMA are revolutionizing the AI industry with their sophisticated capabilities. Training these models requires vast GPU clusters and significant computing time, posing major challenges in terms of scalabilit
Externí odkaz:
http://arxiv.org/abs/2407.20018
Graph Transformer is a new architecture that surpasses GNNs in graph learning. While there emerge inspiring algorithm advancements, their practical adoption is still limited, particularly on real-world graphs involving up to millions of nodes. We obs
Externí odkaz:
http://arxiv.org/abs/2407.14106
Autor:
Gu, Diandian, Sun, Peng, Hu, Qinghao, Huang, Ting, Chen, Xun, Xiong, Yingtong, Wang, Guoteng, Chen, Qiaoling, Zhao, Shangchun, Fang, Jiarui, Wen, Yonggang, Zhang, Tianwei, Jin, Xin, Liu, Xuanzhe
Efficiently training LLMs with long sequences is important yet challenged by the massive computation and memory requirements. Sequence parallelism has been proposed to tackle these problems, but existing methods suffer from scalability or efficiency
Externí odkaz:
http://arxiv.org/abs/2406.18485
Federated learning aims to collaboratively learn a model by using the data from multiple users under privacy constraints. In this paper, we study the multi-label classification problem under the federated learning setting, where trivial solution and
Externí odkaz:
http://arxiv.org/abs/2404.15598
Autor:
Hu, Qinghao, Ye, Zhisheng, Wang, Zerui, Wang, Guoteng, Zhang, Meng, Chen, Qiaoling, Sun, Peng, Lin, Dahua, Wang, Xiaolin, Luo, Yingwei, Wen, Yonggang, Zhang, Tianwei
Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs, often riddled with numerous challenges such as fr
Externí odkaz:
http://arxiv.org/abs/2403.07648
Publikováno v:
ITM Web of Conferences, Vol 47, p 02033 (2022)
At present, most of the existing rumor detection methods focus on the learning and fusion of various features, but due to the complexity of language, these models often rarely consider the relationship between parts of speech. This paper uses graph a
Externí odkaz:
https://doaj.org/article/4a443edd92344e8da6100f5528824e16
Bridging the gap between diffusion models and human preferences is crucial for their integration into practical generative workflows. While optimizing downstream reward models has emerged as a promising alignment strategy, concerns arise regarding th
Externí odkaz:
http://arxiv.org/abs/2402.08552