Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Feng, Yunhe"'
Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health and medicin
Externí odkaz:
http://arxiv.org/abs/2409.10011
Autor:
Xu, Huiyu, Zhang, Wenhui, Wang, Zhibo, Xiao, Feng, Zheng, Rui, Feng, Yunhe, Ba, Zhongjie, Ren, Kui
Recently, advanced Large Language Models (LLMs) such as GPT-4 have been integrated into many real-world applications like Code Copilot. These applications have significantly expanded the attack surface of LLMs, exposing them to a variety of threats.
Externí odkaz:
http://arxiv.org/abs/2407.16667
High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently reduce computations without changing the model, an easy solution is to
Externí odkaz:
http://arxiv.org/abs/2405.17660
The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performance of UAV trackers under common corruptions due to lack of a dedicated
Externí odkaz:
http://arxiv.org/abs/2403.11424
Autor:
Shaik, Kareem, Wang, Dali, Zheng, Weijian, Cao, Qinglei, Fan, Heng, Schwartz, Peter, Feng, Yunhe
The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emergence of generative AI, specifically large language models (LLMs), provi
Externí odkaz:
http://arxiv.org/abs/2403.10588
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approaches often fully fine-tune a dual-branch encoder-decoder framework wit
Externí odkaz:
http://arxiv.org/abs/2312.00360
Machine learning (ML) technologies are known to be riddled with ethical and operational problems, however, we are witnessing an increasing thrust by businesses to deploy them in sensitive applications. One major issue among many is that ML models do
Externí odkaz:
http://arxiv.org/abs/2310.19986
Autor:
Zhang, Boyuan, Tian, Jiannan, Di, Sheng, Yu, Xiaodong, Feng, Yunhe, Liang, Xin, Tao, Dingwen, Cappello, Franck
Today's large-scale scientific applications running on high-performance computing (HPC) systems generate vast data volumes. Thus, data compression is becoming a critical technique to mitigate the storage burden and data-movement cost. However, existi
Externí odkaz:
http://arxiv.org/abs/2304.12557
As recommender systems become increasingly sophisticated and complex, they often suffer from lack of fairness and transparency. Providing robust and unbiased explanations for recommendations has been drawing more and more attention as it can help add
Externí odkaz:
http://arxiv.org/abs/2208.08017
Autor:
Jin, Sian, Zhang, Chengming, Jiang, Xintong, Feng, Yunhe, Guan, Hui, Li, Guanpeng, Song, Shuaiwen Leon, Tao, Dingwen
Training wide and deep neural networks (DNNs) require large amounts of storage resources such as memory because the intermediate activation data must be saved in the memory during forward propagation and then restored for backward propagation. Howeve
Externí odkaz:
http://arxiv.org/abs/2111.09562