Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Gao, Jinyang"'
Autor:
Wu, Tao, Li, Mengze, Chen, Jingyuan, Ji, Wei, Lin, Wang, Gao, Jinyang, Kuang, Kun, Zhao, Zhou, Wu, Fei
Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change caption
Externí odkaz:
http://arxiv.org/abs/2408.12867
Autor:
Wu, Junkang, Xie, Yuexiang, Yang, Zhengyi, Wu, Jiancan, Gao, Jinyang, Ding, Bolin, Wang, Xiang, He, Xiangnan
Direct Preference Optimization (DPO) has emerged as a compelling approach for training Large Language Models (LLMs) to adhere to human preferences. However, the performance of DPO is sensitive to the fine-tuning of its trade-off parameter $\beta$, as
Externí odkaz:
http://arxiv.org/abs/2407.08639
Autor:
Wu, Junkang, Xie, Yuexiang, Yang, Zhengyi, Wu, Jiancan, Chen, Jiawei, Gao, Jinyang, Ding, Bolin, Wang, Xiang, He, Xiangnan
This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes low-quality
Externí odkaz:
http://arxiv.org/abs/2407.07880
Autor:
Tao, Shuchang, Yao, Liuyi, Ding, Hanxing, Xie, Yuexiang, Cao, Qi, Sun, Fei, Gao, Jinyang, Shen, Huawei, Ding, Bolin
Despite the success of large language models (LLMs) in natural language generation, much evidence shows that LLMs may produce incorrect or nonsensical text. This limitation highlights the importance of discerning when to trust LLMs, especially in saf
Externí odkaz:
http://arxiv.org/abs/2404.17287
To support various applications, a prevalent and efficient approach for business owners is leveraging their valuable datasets to fine-tune a pre-trained LLM through the API provided by LLM owners or cloud servers. However, this process carries a subs
Externí odkaz:
http://arxiv.org/abs/2402.14883
Machine learning models have demonstrated remarkable efficacy and efficiency in a wide range of stock forecasting tasks. However, the inherent challenges of data scarcity, including low signal-to-noise ratio (SNR) and data homogeneity, pose significa
Externí odkaz:
http://arxiv.org/abs/2402.06656
Autor:
Chen, Daoyuan, Huang, Yilun, Ma, Zhijian, Chen, Hesen, Pan, Xuchen, Ge, Ce, Gao, Dawei, Xie, Yuexiang, Liu, Zhaoyang, Gao, Jinyang, Li, Yaliang, Ding, Bolin, Zhou, Jingren
The immense evolution in Large Language Models (LLMs) has underscored the importance of massive, heterogeneous, and high-quality data. A data recipe is a mixture of data from different sources for training LLMs, which plays a vital role in LLMs' perf
Externí odkaz:
http://arxiv.org/abs/2309.02033
Recent studies have demonstrated the great power of Transformer models for time series forecasting. One of the key elements that lead to the transformer's success is the channel-independent (CI) strategy to improve the training robustness. However, t
Externí odkaz:
http://arxiv.org/abs/2305.12095
Recently, privacy issues in web services that rely on users' personal data have raised great attention. Unlike existing privacy-preserving technologies such as federated learning and differential privacy, we explore another way to mitigate users' pri
Externí odkaz:
http://arxiv.org/abs/2204.00279
Autor:
Li, Yang, Shen, Yu, Zhang, Wentao, Chen, Yuanwei, Jiang, Huaijun, Liu, Mingchao, Jiang, Jiawei, Gao, Jinyang, Wu, Wentao, Yang, Zhi, Zhang, Ce, Cui, Bin
Publikováno v:
Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD-2021)
Black-box optimization (BBO) has a broad range of applications, including automatic machine learning, engineering, physics, and experimental design. However, it remains a challenge for users to apply BBO methods to their problems at hand with existin
Externí odkaz:
http://arxiv.org/abs/2106.00421