Zobrazeno 1 - 10
of 1 589
pro vyhledávání: '"Zhao, Xun"'
Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the safety protoco
Externí odkaz:
http://arxiv.org/abs/2407.03045
The open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. This includes both base models, which are pre-trained on extensive datasets without alignment, and aligned models, deliberatel
Externí odkaz:
http://arxiv.org/abs/2404.10552
Autor:
Shi, Chenyu, Wang, Xiao, Ge, Qiming, Gao, Songyang, Yang, Xianjun, Gui, Tao, Zhang, Qi, Huang, Xuanjing, Zhao, Xun, Lin, Dahua
Large language models are meticulously aligned to be both helpful and harmless. However, recent research points to a potential overkill which means models may refuse to answer benign queries. In this paper, we investigate the factors for overkill by
Externí odkaz:
http://arxiv.org/abs/2401.17633
Autor:
Li, Qiang, Zhang, Dan, Lei, Shengzhao, Zhao, Xun, Kamnoedboon, Porawit, Li, WeiWei, Dong, Junhao, Li, Shuyan
Despite the promising performance of existing visual models on public benchmarks, the critical assessment of their robustness for real-world applications remains an ongoing challenge. To bridge this gap, we propose an explainable visual dataset, XIMA
Externí odkaz:
http://arxiv.org/abs/2310.08182
Autor:
Yang, Xianjun, Wang, Xiao, Zhang, Qi, Petzold, Linda, Wang, William Yang, Zhao, Xun, Lin, Dahua
Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the essential
Externí odkaz:
http://arxiv.org/abs/2310.02949
Autor:
Guang-Lei Ma, Wan-Qiu Liu, Huawei Huang, Xin-Fu Yan, Wei Shen, Surawit Visitsatthawong, Kridsadakorn Prakinee, Hoa Tran, Xiaohui Fan, Yong-Gui Gao, Pimchai Chaiyen, Jian Li, Zhao-Xun Liang
Publikováno v:
JACS Au, Vol 4, Iss 8, Pp 2925-2935 (2024)
Externí odkaz:
https://doaj.org/article/719a4b5be29445a1bfb02fb5c3b81cc7
Autor:
Zhao, Xun
Titanium has been used in bio-medical implants for decades due to its superior biocompatibility. To improve the osseointegration of dental and orthopaedic implants, various surface modification techniques have been used including laser surface textur
Externí odkaz:
http://hdl.handle.net/10393/42254
Autor:
Shao, Wenqi, Zhao, Xun, Ge, Yixiao, Zhang, Zhaoyang, Yang, Lei, Wang, Xiaogang, Shan, Ying, Luo, Ping
This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be generated by f
Externí odkaz:
http://arxiv.org/abs/2207.03036
Autor:
Yang, Shusheng, Wang, Xinggang, Li, Yu, Fang, Yuxin, Fang, Jiemin, Liu, Wenyu, Zhao, Xun, Shan, Ying
Recently vision transformer has achieved tremendous success on image-level visual recognition tasks. To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeVi
Externí odkaz:
http://arxiv.org/abs/2204.08412
Autor:
Zhao, Xun
Point cloud data can express the 3D features of objects, and is an important data type in the field of 3D object detection. Since point cloud data is more difficult to collect than image data and the scale of existing datasets is smaller, point cloud
Externí odkaz:
http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-311976