Zobrazeno 1 - 10
of 246
pro vyhledávání: '"Hu, Xuming"'
With the widespread use of mobile devices and the rapid growth of micro-video platforms such as TikTok and Kwai, the demand for personalized micro-video recommendation systems has significantly increased. Micro-videos typically contain diverse inform
Externí odkaz:
http://arxiv.org/abs/2409.09638
Large language models (LLMs) have made remarkable progress in various natural language processing tasks as a benefit of their capability to comprehend and reason with factual knowledge. However, a significant amount of factual knowledge is stored in
Externí odkaz:
http://arxiv.org/abs/2408.12188
Hallucination issues persistently plagued current multimodal large language models (MLLMs). While existing research primarily focuses on object-level or attribute-level hallucinations, sidelining the more sophisticated relation hallucinations that ne
Externí odkaz:
http://arxiv.org/abs/2408.09429
The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they
Externí odkaz:
http://arxiv.org/abs/2408.02006
Large Language Models (LLMs) are limited by their parametric knowledge, leading to hallucinations in knowledge-extensive tasks. To address this, Retrieval-Augmented Generation (RAG) incorporates external document chunks to expand LLM knowledge. Furth
Externí odkaz:
http://arxiv.org/abs/2406.11357
Autor:
Zhang, Lingzhe, Jia, Tong, Jia, Mengxi, Wu, Yifan, Liu, Aiwei, Yang, Yong, Wu, Zhonghai, Hu, Xuming, Yu, Philip S., Li, Ying
As software systems grow increasingly intricate, Artificial Intelligence for IT Operations (AIOps) methods have been widely used in software system failure management to ensure the high availability and reliability of large-scale distributed software
Externí odkaz:
http://arxiv.org/abs/2406.11213
MMNeuron: Discovering Neuron-Level Domain-Specific Interpretation in Multimodal Large Language Model
Projecting visual features into word embedding space has become a significant fusion strategy adopted by Multimodal Large Language Models (MLLMs). However, its internal mechanisms have yet to be explored. Inspired by multilingual research, we identif
Externí odkaz:
http://arxiv.org/abs/2406.11193
Driven by the demand for cross-sentence and large-scale relation extraction, document-level relation extraction (DocRE) has attracted increasing research interest. Despite the continuous improvement in performance, we find that existing DocRE models
Externí odkaz:
http://arxiv.org/abs/2406.07444
Autor:
Lai, Songning, Feng, Ninghui, Gao, Jiechao, Wang, Hao, Sui, Haochen, Zou, Xin, Yang, Jiayu, Chen, Wenshuo, Zhao, Hang, Hu, Xuming, Yue, Yutao
Publikováno v:
IJCAI2024 workshop
The field of time series forecasting has garnered significant attention in recent years, prompting the development of advanced models like TimeSieve, which demonstrates impressive performance. However, an analysis reveals certain unfaithfulness issue
Externí odkaz:
http://arxiv.org/abs/2405.19647
Autor:
Pan, Leyi, Liu, Aiwei, He, Zhiwei, Gao, Zitian, Zhao, Xuandong, Lu, Yijian, Zhou, Binglin, Liu, Shuliang, Hu, Xuming, Wen, Lijie, King, Irwin, Yu, Philip S.
LLM watermarking, which embeds imperceptible yet algorithmically detectable signals in model outputs to identify LLM-generated text, has become crucial in mitigating the potential misuse of large language models. However, the abundance of LLM waterma
Externí odkaz:
http://arxiv.org/abs/2405.10051