Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Mu, Yongyu"'
Autor:
Wang, Chenglong, Gan, Yang, Huo, Yifu, Mu, Yongyu, He, Qiaozhi, Yang, Murun, Xiao, Tong, Zhang, Chunliang, Liu, Tongran, Zhu, Jingbo
To improve human-preference alignment training, current research has developed numerous preference datasets consisting of preference pairs labeled as "preferred" or "dispreferred". These preference pairs are typically used to encode human preferences
Externí odkaz:
http://arxiv.org/abs/2410.04503
Autor:
Wang, Chenglong, Gan, Yang, Huo, Yifu, Mu, Yongyu, Yang, Murun, He, Qiaozhi, Xiao, Tong, Zhang, Chunliang, Liu, Tongran, Du, Quan, Yang, Di, Zhu, Jingbo
Large vision-language models (LVLMs) often fail to align with human preferences, leading to issues like generating misleading content without proper visual context (also known as hallucination). A promising solution to this problem is using human-pre
Externí odkaz:
http://arxiv.org/abs/2408.12109
Autor:
Mu, Yongyu, Wu, Yuzhang, Fan, Yuchun, Wang, Chenglong, Li, Hengyu, He, Qiaozhi, Yang, Murun, Xiao, Tong, Zhu, Jingbo
As large language models (LLMs) evolve, the increase in model depth and parameter number leads to substantial redundancy. To enhance the efficiency of the attention mechanism, previous works primarily compress the KV cache or group attention heads, w
Externí odkaz:
http://arxiv.org/abs/2408.01890
Imposing constraints on machine translation systems presents a challenging issue because these systems are not trained to make use of constraints in generating adequate, fluent translations. In this paper, we leverage the capabilities of large langua
Externí odkaz:
http://arxiv.org/abs/2407.13164
Autor:
Wang, Chenglong, Zhou, Hang, Chang, Kaiyan, Li, Bei, Mu, Yongyu, Xiao, Tong, Liu, Tongran, Zhu, Jingbo
Alignment training is crucial for enabling large language models (LLMs) to cater to human intentions and preferences. It is typically performed based on two stages with different objectives: instruction-following alignment and human-preference alignm
Externí odkaz:
http://arxiv.org/abs/2406.15178
Autor:
Mu, Yongyu, Feng, Peinan, Cao, Zhiquan, Wu, Yuzhang, Li, Bei, Wang, Chenglong, Xiao, Tong, Song, Kai, Liu, Tongran, Zhang, Chunliang, Zhu, Jingbo
In this study, we reveal an in-context learning (ICL) capability of multilingual large language models (LLMs): by translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly enhances
Externí odkaz:
http://arxiv.org/abs/2403.09073
Autor:
Mu, Yongyu, Reheman, Abudurexiti, Cao, Zhiquan, Fan, Yuchun, Li, Bei, Li, Yinqiao, Xiao, Tong, Zhang, Chunliang, Zhu, Jingbo
Using translation memories (TMs) as prompts is a promising approach to in-context learning of machine translation models. In this work, we take a step towards prompting large language models (LLMs) with TMs and making them better translators. We find
Externí odkaz:
http://arxiv.org/abs/2305.17367
Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use of them t
Externí odkaz:
http://arxiv.org/abs/2302.00444
Autor:
Zhou, Shuhan, Zhou, Tao, Wei, Binghao, Luo, Yingfeng, Mu, Yongyu, Zhou, Zefan, Wang, Chenglong, Zhou, Xuanjun, Lv, Chuanhao, Jing, Yi, Wang, Laohu, Zhang, Jingnan, Huang, Canan, Yan, Zhongxiang, Hu, Chi, Li, Bei, Xiao, Tong, Zhu, Jingbo
This paper describes NiuTrans neural machine translation systems of the WMT 2021 news translation tasks. We made submissions to 9 language directions, including English$\leftrightarrow$$\{$Chinese, Japanese, Russian, Icelandic$\}$ and English$\righta
Externí odkaz:
http://arxiv.org/abs/2109.10485
Autor:
Wang, Chenglong, Hu, Chi, Mu, Yongyu, Yan, Zhongxiang, Wu, Siming, Hu, Minyi, Cao, Hang, Li, Bei, Lin, Ye, Xiao, Tong, Zhu, Jingbo
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt.org/wmt21/efficiency-task.html). Following last year's work, we explore various techniques to improve efficiency while maintaining translation quality.
Externí odkaz:
http://arxiv.org/abs/2109.08003