Zobrazeno 1 - 10
of 23 287
pro vyhledávání: '"AN Xiao-jing"'
Large language models (LLMs) often suffer from context faithfulness hallucinations, where outputs deviate from retrieved information due to insufficient context utilization and high output uncertainty. Our uncertainty evaluation experiments reveal a
Externí odkaz:
http://arxiv.org/abs/2501.01059
Layer removal has emerged as a promising approach for compressing large language models (LLMs) by leveraging redundancy within layers to reduce model size and accelerate inference. However, this technique often compromises internal consistency, leadi
Externí odkaz:
http://arxiv.org/abs/2501.00339
Vehicle detection and tracking in satellite video is essential in remote sensing (RS) applications. However, upon the statistical analysis of existing datasets, we find that the dim vehicles with low radiation intensity and limited contrast against t
Externí odkaz:
http://arxiv.org/abs/2412.18214
Autor:
Li, Hong-Wei, Fan, Yi-Hao, Shen, Shu-Ting, Yan, Xiao-Jing, Li, Xi-Yun, Zhong, Wei, Sheng, Yu-Bo, Zhou, Lan, Du, Ming-Ming
Publikováno v:
Eur. Phys. J. C 84, 1241 (2024)
Quantum coherence, a fundamental aspect of quantum mechanics, plays a crucial role in various quantum information tasks. However, preserving coherence under extreme conditions, such as relativistic acceleration, poses significant challenges. In this
Externí odkaz:
http://arxiv.org/abs/2411.19254
The audio watermarking technique embeds messages into audio and accurately extracts messages from the watermarked audio. Traditional methods develop algorithms based on expert experience to embed watermarks into the time-domain or transform-domain of
Externí odkaz:
http://arxiv.org/abs/2409.19627
Autor:
Li, Zhangpu, Zou, Changhong, Ma, Suxue, Yang, Zhicheng, Du, Chen, Tang, Youbao, Cao, Zhenjie, Zhang, Ning, Lai, Jui-Hsin, Lin, Ruei-Sung, Ni, Yuan, Sun, Xingzhi, Xiao, Jing, Hou, Jieke, Zhang, Kai, Han, Mei
The rocketing prosperity of large language models (LLMs) in recent years has boosted the prevalence of vision-language models (VLMs) in the medical sector. In our online medical consultation scenario, a doctor responds to the texts and images provide
Externí odkaz:
http://arxiv.org/abs/2409.17610
Knowledge tracing is a technique that predicts students' future performance by analyzing their learning process through historical interactions with intelligent educational platforms, enabling a precise evaluation of their knowledge mastery. Recent s
Externí odkaz:
http://arxiv.org/abs/2409.06745
Online Domain Adaptation (OnDA) is designed to handle unforeseeable domain changes at minimal cost that occur during the deployment of the model, lacking clear boundaries between the domain, such as sudden weather events. However, existing OnDA metho
Externí odkaz:
http://arxiv.org/abs/2409.01072
Significant advancements in Large Multimodal Models (LMMs) have enabled them to tackle complex problems involving visual-mathematical reasoning. However, their ability to identify geometric elements remains underexplored. To address this gap, we intr
Externí odkaz:
http://arxiv.org/abs/2408.13854
Autor:
Du, Ming-Ming, Li, Hong-Wei, Shen, Shu-Ting, Yan, Xiao-Jing, Li, Xi-Yun, Zhou, Lan, Zhong, Wei, Sheng, Yu-Bo
In the past two decades, the exploration of quantumness within Schwarzschild spacetime has garnered significant interest, particularly regarding the Hawking radiation's impact on quantum correlations and quantum coherence. Building on this foundation
Externí odkaz:
http://arxiv.org/abs/2408.12395