Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Zhang, Songming"'
Autor:
Xiao, Xiongtao, Chen, Xiaofeng, Jiang, Feiyan, Zhang, Songming, Cao, Wenming, Tan, Cheng, Gao, Zhangyang, Li, Zhongshan
Single-cell spatial transcriptomics (ST) offers a unique approach to measuring gene expression profiles and spatial cell locations simultaneously. However, most existing ST methods assume that cells in closer spatial proximity exhibit more similar ge
Externí odkaz:
http://arxiv.org/abs/2410.20159
Knowledge distillation (KD) is known as a promising solution to compress large language models (LLMs) via transferring their knowledge to smaller models. During this process, white-box KD methods usually minimize the distance between the output distr
Externí odkaz:
http://arxiv.org/abs/2406.17328
Autor:
zhang, Xue, Liang, Yunlong, Meng, Fandong, Zhang, Songming, Chen, Yufeng, Xu, Jinan, Zhou, Jie
Multilingual knowledge editing (MKE) aims to simultaneously revise factual knowledge across multilingual languages within large language models (LLMs). However, most existing MKE methods just adapt existing monolingual editing methods to multilingual
Externí odkaz:
http://arxiv.org/abs/2406.16416
Deep neural networks often face generalization problems to handle out-of-distribution (OOD) data, and there remains a notable theoretical gap between the contributing factors and their respective impacts. Literature evidence from in-distribution data
Externí odkaz:
http://arxiv.org/abs/2312.16243
Knowledge distillation transfers knowledge from large models into small models, and has recently made remarkable achievements. However, few studies has investigated the mechanism of knowledge distillation against distribution shift. Distribution shif
Externí odkaz:
http://arxiv.org/abs/2312.16242
Autor:
Zhang, Xue, Zhang, Songming, Liang, Yunlong, Chen, Yufeng, Liu, Jian, Han, Wenjuan, Xu, Jinan
Existing syntactically-controlled paraphrase generation (SPG) models perform promisingly with human-annotated or well-chosen syntactic templates. However, the difficulty of obtaining such templates actually hinders the practical application of SPG mo
Externí odkaz:
http://arxiv.org/abs/2310.13262
Autor:
Zhang, Songming, Liang, Yunlong, Wang, Shuaibo, Han, Wenjuan, Liu, Jian, Xu, Jinan, Chen, Yufeng
Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel this mystery
Externí odkaz:
http://arxiv.org/abs/2305.08096
Translation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT'22 Translation Suggesti
Externí odkaz:
http://arxiv.org/abs/2210.06138
Token-level adaptive training approaches can alleviate the token imbalance problem and thus improve neural machine translation, through re-weighting the losses of different target tokens based on specific statistical metrics (e.g., token frequency or
Externí odkaz:
http://arxiv.org/abs/2203.02951
Publikováno v:
In Engineering Applications of Artificial Intelligence July 2024 133 Part C
