Zobrazeno 1 - 10
of 1 754
pro vyhledávání: '"Li,Shijun"'
The success of large language models (LLMs) has fostered a new research trend of multi-modality large language models (MLLMs), which changes the paradigm of various fields in computer vision. Though MLLMs have shown promising results in numerous high
Externí odkaz:
http://arxiv.org/abs/2405.15734
Domain generalization faces challenges due to the distribution shift between training and testing sets, and the presence of unseen target domains. Common solutions include domain alignment, meta-learning, data augmentation, or ensemble learning, all
Externí odkaz:
http://arxiv.org/abs/2404.13848
Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource limitations. Wh
Externí odkaz:
http://arxiv.org/abs/2404.12588
The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts. However, human thought processes are predo
Externí odkaz:
http://arxiv.org/abs/2404.04538
Autor:
Zhang, Gangyi, Gao, Chongming, Lei, Wenqiang, Guo, Xiaojie, Li, Shijun, Chen, Hongshen, Ding, Zhuozhi, Xu, Sulong, Wu, Lingfei
Conversational recommendation systems (CRS) commonly assume users have clear preferences, leading to potential over-filtering of relevant alternatives. However, users often exhibit vague, non-binary preferences. We introduce the Vague Preference Mult
Externí odkaz:
http://arxiv.org/abs/2306.04487
Autor:
Xia, Xiangbin1 (AUTHOR) xiaxiangbin@hxtzbyq.com, Li, Shijun2 (AUTHOR) 70003@hnie.edu.cn, Luo, Derong3 (AUTHOR) yuxu98@hnu.edu.cn, Chen, Sen1 (AUTHOR) zhiliang@hxtzbyq.com, Liu, Jing1 (AUTHOR) lijia@hxtzbyq.com, Yao, Jiacheng1 (AUTHOR) caigou@hxtzbyq.com, Wu, Liren1 (AUTHOR) shouhou@hxtzbyq.com, Zhang, Ximing1 (AUTHOR) xiamiao@hxtzbyq.com
Publikováno v:
Energies (19961073). Sep2024, Vol. 17 Issue 17, p4251. 22p.
Autor:
Gao, Chongming, Li, Shijun, Zhang, Yuan, Chen, Jiawei, Li, Biao, Lei, Wenqiang, Jiang, Peng, He, Xiangnan
Recommender systems deployed in real-world applications can have inherent exposure bias, which leads to the biased logged data plaguing the researchers. A fundamental way to address this thorny problem is to collect users' interactions on randomly ex
Externí odkaz:
http://arxiv.org/abs/2208.08696
Autor:
Gao, Chongming, Wang, Shiqi, Li, Shijun, Chen, Jiawei, He, Xiangnan, Lei, Wenqiang, Li, Biao, Zhang, Yuan, Jiang, Peng
While personalization increases the utility of recommender systems, it also brings the issue of filter bubbles. E.g., if the system keeps exposing and recommending the items that the user is interested in, it may also make the user feel bored and les
Externí odkaz:
http://arxiv.org/abs/2204.01266
Publikováno v:
In Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy 5 November 2024 320
Publikováno v:
In Poultry Science November 2024 103(11)