Zobrazeno 1 - 10
of 271
pro vyhledávání: '"Zeng Zhixiong"'
Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in performance degrad
Externí odkaz:
http://arxiv.org/abs/2410.03743
Autor:
Wei, Yanbin, Fu, Shuai, Jiang, Weisen, Zhang, Zejian, Zeng, Zhixiong, Wu, Qi, Kwok, James T., Zhang, Yu
Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend stru
Externí odkaz:
http://arxiv.org/abs/2402.02130
Recently, Locate-Then-Edit paradigm has emerged as one of the main approaches in changing factual knowledge stored in the Language models. However, there is a lack of research on whether present locating methods can pinpoint the exact parameters embe
Externí odkaz:
http://arxiv.org/abs/2309.16535
Publikováno v:
E3S Web of Conferences, Vol 195, p 03043 (2020)
Compacted MX80 bentonite/Callovo-Oxfordian (COx) claystone mixture has been considered as a possible sealing/backfilling material in the French deep geological radioactive waste disposal. The swelling pressure of such mixture is an important factor i
Externí odkaz:
https://doaj.org/article/af3e5268a5bc42bcbd04d9068aa236e3
Autor:
Wang, Binbin, Li, Mingming, Zeng, Zhixiong, Zhuo, Jingwei, Wang, Songlin, Xu, Sulong, Long, Bo, Yan, Weipeng
Retrieving relevant items that match users' queries from billion-scale corpus forms the core of industrial e-commerce search systems, in which embedding-based retrieval (EBR) methods are prevailing. These methods adopt a two-tower framework to learn
Externí odkaz:
http://arxiv.org/abs/2303.11009
Publikováno v:
In Tribology International January 2025 201
Publikováno v:
In Smart Agricultural Technology December 2024 9
Autor:
Zeng, Zhixiong, Mao, Wenji
Cross-Modal Retrieval (CMR) is an important research topic across multimodal computing and information retrieval, which takes one type of data as the query to retrieve relevant data of another type. It has been widely used in many real-world applicat
Externí odkaz:
http://arxiv.org/abs/2201.02772
Autor:
Xu, Guohai, Chen, Hehong, Li, Feng-Lin, Sun, Fu, Shi, Yunzhou, Zeng, Zhixiong, Zhou, Wei, Zhao, Zhongzhou, Zhang, Ji
Live streaming is becoming an increasingly popular trend of sales in E-commerce. The core of live-streaming sales is to encourage customers to purchase in an online broadcasting room. To enable customers to better understand a product without jumping
Externí odkaz:
http://arxiv.org/abs/2109.07411
Publikováno v:
In Structure 11 July 2024 32(7):889-898