Zobrazeno 1 - 10
of 4 547
pro vyhledávání: '"Xiong, Hui"'
Autor:
Gao, Mingze, Liu, Jingyu, Li, Mingda, Xie, Jiangtao, Liu, Qingbin, Zhao, Bo, Chen, Xi, Xiong, Hui
Multimodal Large Language Models (MLLMs) have significantly improved performance across various image-language applications. Recently, there has been a growing interest in adapting image pre-trained MLLMs for video-related tasks. However, most effort
Externí odkaz:
http://arxiv.org/abs/2409.03206
Autor:
Chen, Yiran, Rao, Anyi, Jiang, Xuekun, Xiao, Shishi, Ma, Ruiqing, Wang, Zeyu, Xiong, Hui, Dai, Bo
With advancements in video generative AI models (e.g., SORA), creators are increasingly using these techniques to enhance video previsualization. However, they face challenges with incomplete and mismatched AI workflows. Existing methods mainly rely
Externí odkaz:
http://arxiv.org/abs/2408.17424
Backdoor attacks present a serious security threat to deep neuron networks (DNNs). Although numerous effective defense techniques have been proposed in recent years, they inevitably rely on the availability of either clean or poisoned data. In contra
Externí odkaz:
http://arxiv.org/abs/2408.15861
Autor:
Cao, Xiong-Hui, Guo, Zhi-Hui
We calculate the amplitudes of the axion photoproduction off the nucleon, i.e., $\gamma N \to a N$, within the framework of chiral effective field theory. Several different types of contributions are simultaneously included in our calculation, namely
Externí odkaz:
http://arxiv.org/abs/2408.15825
Autor:
Xiong, Hui, Zhu, Mengcheng
Classical mechanics and geometrical optics are deeply connected with each other. In this work, we generalize the analogy between these two disciplines to relativistic conditions. Using this analogy, we are able to make light follow the orbits of mass
Externí odkaz:
http://arxiv.org/abs/2408.10723
Autor:
Ye, Yuyang, Zheng, Zhi, Shen, Yishan, Wang, Tianshu, Zhang, Hengruo, Zhu, Peijun, Yu, Runlong, Zhang, Kai, Xiong, Hui
Recent advances in Large Language Models (LLMs) have demonstrated significant potential in the field of Recommendation Systems (RSs). Most existing studies have focused on converting user behavior logs into textual prompts and leveraging techniques s
Externí odkaz:
http://arxiv.org/abs/2408.09698
Pre-trained Language Models (PLMs), such as ChatGPT, have significantly advanced the field of natural language processing. This progress has inspired a series of innovative studies that explore the adaptation of PLMs to time series analysis, intendin
Externí odkaz:
http://arxiv.org/abs/2408.08328
Self-supervised learning (SSL) has recently achieved significant success in downstream visual tasks. However, a notable gap still exists between SSL and supervised learning (SL), especially in complex downstream tasks. In this paper, we show that the
Externí odkaz:
http://arxiv.org/abs/2407.13541
Autor:
Ye, Yuyang, Tang, Lu-An, Wang, Haoyu, Yu, Runlong, Yu, Wenchao, He, Erhu, Chen, Haifeng, Xiong, Hui
Achieving carbon neutrality within industrial operations has become increasingly imperative for sustainable development. It is both a significant challenge and a key opportunity for operational optimization in industry 4.0. In recent years, Deep Rein
Externí odkaz:
http://arxiv.org/abs/2407.08910
Autor:
Hu, Zhengyu, Song, Linxin, Zhang, Jieyu, Xiao, Zheyuan, Wang, Jingang, Chen, Zhenyu, Xiong, Hui
The use of large language model (LLM)-based preference evaluations has become widespread for comparing model responses, but it has revealed a notable bias towards longer responses, questioning the reliability of such evaluations. This paper explores
Externí odkaz:
http://arxiv.org/abs/2407.01085