Zobrazeno 1 - 10
of 673
pro vyhledávání: '"Huang, Yongfeng."'
Autor:
Liao, Jie, Chang, Ning, Cui, Lang, Jiang, Pengfei, Mou, Didong, Huang, Yongfeng, An, Tao, Ho, Luis C., Feng, Hua, Fu, Yu-Cong, Cao, Hongmin, Liu, Xiang
Type-C quasi-periodic oscillations (QPOs) in black hole X-ray transients typically manifest in the low-hard and hard-intermediate states. This study presents a detailed spectral and temporal analysis of the black hole candidate Swift J1727.8-1613 usi
Externí odkaz:
http://arxiv.org/abs/2410.06574
Autor:
Yu, Yijiong, Xiufa, Ma, Jianwei, Fang, Xu, Zhi, Guangyao, Su, Jiancheng, Wang, Huang, Yongfeng, Qi, Zhixiao, Wang, Wei, Liu, Weifeng, Chen, Ran, Pei, Ji
Long-context language models (LCLMs), characterized by their extensive context window, are becoming increasingly popular. However, despite they are nearly perfect at standard long-context retrieval, we find they are actually not good at all of them.
Externí odkaz:
http://arxiv.org/abs/2410.04422
Autor:
Lai, Jiahao, Li, Jiaqi, Xu, Jian, Wu, Yanru, Tang, Boshi, Chen, Siqi, Huang, Yongfeng, Ding, Wenbo, Li, Yang
Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly a
Externí odkaz:
http://arxiv.org/abs/2409.05701
Autor:
Yang, Zhen, Wang, Wenhui, Qi, Tao, Zhang, Peng, Zhang, Tianyun, Zhang, Ru, Liu, Jianyi, Huang, Yongfeng
Accurately recommending candidate news articles to users has always been the core challenge of news recommendation system. News recommendations often require modeling of user interest to match candidate news. Recent efforts have primarily focused on
Externí odkaz:
http://arxiv.org/abs/2408.00859
Text style transfer, an important research direction in natural language processing, aims to adapt the text to various preferences but often faces challenges with limited resources. In this work, we introduce a novel method termed Style Extraction an
Externí odkaz:
http://arxiv.org/abs/2407.15556
To circumvent the unbridled and ever-encroaching surveillance and censorship in cyberspace, steganography has garnered attention for its ability to hide private information in innocent-looking carriers. Current provably secure steganography approache
Externí odkaz:
http://arxiv.org/abs/2407.13499
Autor:
Yu, Yijiong, Jiang, Huiqiang, Luo, Xufang, Wu, Qianhui, Lin, Chin-Yew, Li, Dongsheng, Yang, Yuqing, Huang, Yongfeng, Qiu, Lili
Large Language Models (LLMs) are increasingly applied in various real-world scenarios due to their excellent generalization capabilities and robust generative abilities. However, they exhibit position bias, also known as "lost in the middle", a pheno
Externí odkaz:
http://arxiv.org/abs/2406.02536
Linguistic steganography provides convenient implementation to hide messages, particularly with the emergence of AI generation technology. The potential abuse of this technology raises security concerns within societies, calling for powerful linguist
Externí odkaz:
http://arxiv.org/abs/2405.09090
Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user access only in
Externí odkaz:
http://arxiv.org/abs/2405.02365
In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on signal insertio
Externí odkaz:
http://arxiv.org/abs/2405.01509