Zobrazeno 1 - 10
of 1 360
pro vyhledávání: '"Li, Xiao‐hui"'
Autor:
Deng, Chao, Yuan, Jiale, Bu, Pi, Wang, Peijie, Li, Zhong-Zhi, Xu, Jian, Li, Xiao-Hui, Gao, Yuan, Song, Jun, Zheng, Bo, Liu, Cheng-Lin
Large vision language models (LVLMs) have improved the document understanding capabilities remarkably, enabling the handling of complex document elements, longer contexts, and a wider range of tasks. However, existing document understanding benchmark
Externí odkaz:
http://arxiv.org/abs/2412.18424
We study theoretically the nonlinear optical response of disordered electrons in the regime of weak (anti)localization. Our analytical and numerical calculations reveal that, in orthogonal/symplectic class systems, two consecutive, phase coherent opt
Externí odkaz:
http://arxiv.org/abs/2404.16867
The need to explain the output of a deep neural network classifier is now widely recognized. While previous methods typically explain a single class in the output, we advocate explaining the whole output, which is a probability distribution over mult
Externí odkaz:
http://arxiv.org/abs/2306.06339
Despite the popularity of Vision Transformers (ViTs) and eXplainable AI (XAI), only a few explanation methods have been designed specially for ViTs thus far. They mostly use attention weights of the [CLS] token on patch embeddings and often produce u
Externí odkaz:
http://arxiv.org/abs/2211.03064
Autor:
Nie, Wei a, b, Feng, Li-Ping a, b, Wan, Jin-Fu a, b, Li, Xiao-Hui a, b, Zhang, Ying-Jie a, b, Fu, De-Huan a, b, Li, Qian a, b, c, ⁎
Publikováno v:
In Biochemical Systematics and Ecology April 2025 119
Autor:
Zhang, Nevin L., Xie, Weiyan, Lin, Zhi, Dong, Guanfang, Li, Xiao-Hui, Cao, Caleb Chen, Wang, Yunpeng
Some examples are easier for humans to classify than others. The same should be true for deep neural networks (DNNs). We use the term example perplexity to refer to the level of difficulty of classifying an example. In this paper, we propose a method
Externí odkaz:
http://arxiv.org/abs/2203.08813
Publikováno v:
In Electronic Commerce Research and Applications March-April 2024 64
It has been long debated that eXplainable AI (XAI) is an important topic, but it lacks rigorous definition and fair metrics. In this paper, we briefly summarize the status quo of the metrics, along with an exhaustive experimental study based on them,
Externí odkaz:
http://arxiv.org/abs/2012.15616
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Optical Fiber Technology January 2024 82