Zobrazeno 1 - 10
of 304
pro vyhledávání: '"Ma, Can"'
Large Language Models (LLMs) have demonstrated exceptional proficiency in mathematical reasoning tasks due to their extensive parameter counts and training on vast datasets. Despite these capabilities, deploying LLMs is hindered by their computationa
Externí odkaz:
http://arxiv.org/abs/2407.10167
With the proliferation of social media posts in recent years, the need to detect sentiments in multimodal (image-text) content has grown rapidly. Since posts are user-generated, the image and text from the same post can express different or even cont
Externí odkaz:
http://arxiv.org/abs/2407.07026
This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We introduce E
Externí odkaz:
http://arxiv.org/abs/2401.11864
Autor:
Li, Shujie, Li, Liang, Geng, Ruiying, Yang, Min, Li, Binhua, Yuan, Guanghu, He, Wanwei, Yuan, Shao, Ma, Can, Huang, Fei, Li, Yongbin
Data-to-text (D2T) generation aims to transform structured data into natural language text. Data-to-text pre-training has proved to be powerful in enhancing D2T generation and yields impressive performances. However, previous pre-training methods eit
Externí odkaz:
http://arxiv.org/abs/2401.01183
Text-based Visual Question Answering (TextVQA) aims at answering questions about the text in images. Most works in this field focus on designing network structures or pre-training tasks. All these methods list the OCR texts in reading order (from lef
Externí odkaz:
http://arxiv.org/abs/2308.16383
Large Language Models (LLMs) have transformed natural language processing tasks successfully. Yet, their large size and high computational needs pose challenges for practical use, especially in resource-limited settings. Model compression has emerged
Externí odkaz:
http://arxiv.org/abs/2308.07633
Autor:
Li, Liang, Geng, Ruiying, Fang, Chengyang, Li, Bing, Ma, Can, Cao, Rongyu, Li, Binhua, Huang, Fei, Li, Yongbin
There are three problems existing in the popular data-to-text datasets. First, the large-scale datasets either contain noise or lack real application scenarios. Second, the datasets close to real applications are relatively small in size. Last, curre
Externí odkaz:
http://arxiv.org/abs/2306.11477
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables. Recent works explicitly decompose the generation process into content planning and surface generation stages, employing t
Externí odkaz:
http://arxiv.org/abs/2302.05138
Autor:
Xiao, Xia1,2,3 (AUTHOR) 006503@yzu.edu.cn, Ma, Can1 (AUTHOR) macan18652592290@outlook.com, Zhang, Han1 (AUTHOR) m15609938315@163.com, Liu, Wei1 (AUTHOR) lw15264770396@163.com, Huang, Yanhu1 (AUTHOR) dx120230185@stu.yzu.edu.cn, Meng, Chuang2,3 (AUTHOR), Wang, Zhiqiang1,2,4 (AUTHOR) zqwang@yzu.edu.cn
Publikováno v:
International Journal of Molecular Sciences. Aug2024, Vol. 25 Issue 16, p8843. 18p.
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism. Recent studies have shown that explicitly modeling the input graph structure can significantly improve the performance. However, the vanilla structura
Externí odkaz:
http://arxiv.org/abs/2209.07258