Zobrazeno 61 - 70
of 39 213
pro vyhledávání: '"Chen, Liang"'
Do large language models (LLMs) genuinely understand the semantics of the language, or just memorize the training data? The recent concern on potential data contamination of LLMs has raised awareness of the community to conduct research on LLMs evalu
Externí odkaz:
http://arxiv.org/abs/2310.01448
Autor:
Zhu, Alex Zihao, Mei, Jieru, Qiao, Siyuan, Yan, Hang, Zhu, Yukun, Chen, Liang-Chieh, Kretzschmar, Henrik
Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to the high dimensionality of this task, most existing approaches use local
Externí odkaz:
http://arxiv.org/abs/2309.16889
We propose new results for the existence and uniqueness of a general nonparametric and nonseparable competitive equilibrium with substitutes. These results ensure the invertibility of a general competitive system. The existing literature has focused
Externí odkaz:
http://arxiv.org/abs/2309.11416
Autor:
Zhao, Haozhe, Cai, Zefan, Si, Shuzheng, Ma, Xiaojian, An, Kaikai, Chen, Liang, Liu, Zixuan, Wang, Sheng, Han, Wenjuan, Chang, Baobao
Since the resurgence of deep learning, vision-language models (VLMs) enhanced by large language models (LLMs) have grown exponentially in popularity. However, while LLMs can utilize extensive background knowledge and task information with in-context
Externí odkaz:
http://arxiv.org/abs/2309.07915
Autor:
Wang, Peiyi, Li, Lei, Chen, Liang, Song, Feifan, Lin, Binghuai, Cao, Yunbo, Liu, Tianyu, Sui, Zhifang
Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal that fine
Externí odkaz:
http://arxiv.org/abs/2309.02144
Real numbers provide a sufficient description of classical physics and all measurable phenomena; however, complex numbers are occasionally utilized as a convenient mathematical tool to aid our calculations. On the other hand, the formalism of quantum
Externí odkaz:
http://arxiv.org/abs/2308.16399
Two-dimensional (2D) materials, with their structural uniqueness, exceptional properties, and wide-ranging applications, show unprecedented prospects in fundamental physics research and industrial applications. 2D \b{eta}-phase cuprous iodide (\b{eta
Externí odkaz:
http://arxiv.org/abs/2308.15708
The Nesterov accelerated gradient (NAG) method is an important extrapolation-based numerical algorithm that accelerates the convergence of the gradient descent method in convex optimization. When dealing with an objective function that is $\mu$-stron
Externí odkaz:
http://arxiv.org/abs/2308.14080
This paper offers a new perspective to ease the challenge of domain generalization, which involves maintaining robust results even in unseen environments. Our design focuses on the decision-making process in the final classifier layer. Specifically,
Externí odkaz:
http://arxiv.org/abs/2308.11158
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in representation learning for graphs recently. However, the effectiveness of GNNs, which capitalize on the key operation of message propagation, highly depends on the quality of
Externí odkaz:
http://arxiv.org/abs/2308.06801