Zobrazeno 1 - 10
of 3 020
pro vyhledávání: '"Li, ShaSha"'
Autor:
Song, Shezheng, Li, Shasha, Yu, Jie, Zhao, Shan, Li, Xiaopeng, Ma, Jun, Liu, Xiaodong, Li, Zhuo, Mao, Xiaoguang
Our study delves into Multimodal Entity Linking, aligning the mention in multimodal information with entities in knowledge base. Existing methods are still facing challenges like ambiguous entity representations and limited image information utilizat
Externí odkaz:
http://arxiv.org/abs/2407.12019
Autor:
Song, Shezheng, Li, Shasha, Zhao, Shan, Wang, Chengyu, Li, Xiaopeng, Yu, Jie, Wan, Qian, Ma, Jun, Yan, Tianwei, Ma, Wentao, Mao, Xiaoguang
Multimodal aspect-based sentiment analysis (MABSA) aims to understand opinions in a granular manner, advancing human-computer interaction and other fields. Traditionally, MABSA methods use a joint prediction approach to identify aspects and sentiment
Externí odkaz:
http://arxiv.org/abs/2406.00017
Autor:
Zuo, Wenwen, Guo, Hengxiao, Sun, Jingbo, Yuan, Qi, Lira, Paulina, Gu, Minfeng, Edwards, Philip G., Gupta, Alok C., Kishore, Shubham, Stevens, Jamie, An, Tao, Cai, Zhen-Yi, Feng, Haicheng, Ho, Luis C., Ilić, Dragana, Kovačević, Andjelka B., Li, ShaSha, Mezcua, Mar, Popović, Luka Č., Sun, Mouyuan, Tripathi, Tushar, U., Vivian, Vince, Oliver, Wang, Jianguo, Wang, Junxian, Wang, Shu, Wu, Xuebing, Zheng, Zhenya
To investigate the short-term variability and determine the size of the optical continuum emitting size of intermediate-mass black holes (IMBHs), we carried out high-cadence, multi-band photometric monitoring of a Seyfert 1 galaxy J0249-0815 across t
Externí odkaz:
http://arxiv.org/abs/2405.11750
Automatically condensing multiple topic-related scientific papers into a succinct and concise summary is referred to as Multi-Document Scientific Summarization (MDSS). Currently, while commonly used abstractive MDSS methods can generate flexible and
Externí odkaz:
http://arxiv.org/abs/2404.10416
Autor:
Song, Shezheng, Li, Shasha, Zhao, Shan, Li, Xiaopeng, Wang, Chengyu, Yu, Jie, Ma, Jun, Yan, Tianwei, Ji, Bin, Mao, Xiaoguang
Multimodal entity linking (MEL) aims to utilize multimodal information (usually textual and visual information) to link ambiguous mentions to unambiguous entities in knowledge base. Current methods facing main issues: (1)treating the entire image as
Externí odkaz:
http://arxiv.org/abs/2404.04818
Citing comprehensively and appropriately has become a challenging task with the explosive growth of scientific publications. Current citation recommendation systems aim to recommend a list of scientific papers for a given text context or a draft pape
Externí odkaz:
http://arxiv.org/abs/2403.01873
Autor:
Li, Xiaopeng, Li, Shasha, Song, Shezheng, Liu, Huijun, Ji, Bin, Wang, Xi, Ma, Jun, Yu, Jie, Liu, Xiaodong, Wang, Jing, Zhang, Weimin
The general capabilities of large language models (LLMs) make them the infrastructure for various AI applications, but updating their inner knowledge requires significant resources. Recent model editing is a promising technique for efficiently updati
Externí odkaz:
http://arxiv.org/abs/2401.17809
Autor:
Song, Shezheng, Zhao, Shan, Wang, Chengyu, Yan, Tianwei, Li, Shasha, Mao, Xiaoguang, Wang, Meng
Multimodal Entity Linking (MEL) aims at linking ambiguous mentions with multimodal information to entity in Knowledge Graph (KG) such as Wikipedia, which plays a key role in many applications. However, existing methods suffer from shortcomings, inclu
Externí odkaz:
http://arxiv.org/abs/2312.11816
Autor:
Song, Shezheng, Li, Xiaopeng, Li, Shasha, Zhao, Shan, Yu, Jie, Ma, Jun, Mao, Xiaoguang, Zhang, Weimin
This review paper explores Multimodal Large Language Models (MLLMs), which integrate Large Language Models (LLMs) like GPT-4 to handle multimodal data such as text and vision. MLLMs demonstrate capabilities like generating image narratives and answer
Externí odkaz:
http://arxiv.org/abs/2311.07594
Model editing techniques modify a minor proportion of knowledge in Large Language Models (LLMs) at a relatively low cost, which have demonstrated notable success. Existing methods assume Transformer Layer (TL) hidden states are values of key-value me
Externí odkaz:
http://arxiv.org/abs/2308.08742