Zobrazeno 1 - 10
of 640
pro vyhledávání: '"ZHU ZIWEI"'
Autor:
Ren, Jinke, Sun, Yaping, Du, Hongyang, Yuan, Weiwen, Wang, Chongjie, Wang, Xianda, Zhou, Yingbin, Zhu, Ziwei, Wang, Fangxin, Cui, Shuguang
This paper delves into the applications of generative artificial intelligence (GAI) in semantic communication (SemCom) and presents a thorough study. Three popular SemCom systems enabled by classical GAI models are first introduced, including variati
Externí odkaz:
http://arxiv.org/abs/2412.08642
Cross-domain recommendation (CDR) has emerged as a promising solution to the cold-start problem, faced by single-domain recommender systems. However, existing CDR models rely on complex neural architectures, large datasets, and significant computatio
Externí odkaz:
http://arxiv.org/abs/2411.19862
Effective labeled data collection plays a critical role in developing and fine-tuning robust streaming analytics systems. However, continuously labeling documents to filter relevant information poses significant challenges like limited labeling budge
Externí odkaz:
http://arxiv.org/abs/2411.18060
Autor:
Zhou, Yuqing, Zhu, Ziwei
In text classification tasks, models often rely on spurious correlations for predictions, incorrectly associating irrelevant features with the target labels. This issue limits the robustness and generalization of models, especially when faced with ou
Externí odkaz:
http://arxiv.org/abs/2411.01045
Autor:
Wei, Bowen, Zhu, Ziwei
Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel prototype
Externí odkaz:
http://arxiv.org/abs/2410.17546
Publikováno v:
Findings of EMNLP 2024
Language models (LMs), despite their advances, often depend on spurious correlations, undermining their accuracy and generalizability. This study addresses the overlooked impact of subtler, more complex shortcuts that compromise model reliability bey
Externí odkaz:
http://arxiv.org/abs/2409.17455
The United States has experienced a significant increase in violent extremism, prompting the need for automated tools to detect and limit the spread of extremist ideology online. This study evaluates the performance of Bidirectional Encoder Represent
Externí odkaz:
http://arxiv.org/abs/2408.16749
Autor:
Wei, Bowen, Zhu, Ziwei
Rule-based neural networks stand out for enabling interpretable classification by learning logical rules for both prediction and interpretation. However, existing models often lack flexibility due to the fixed model structure. Addressing this, we int
Externí odkaz:
http://arxiv.org/abs/2408.11918
We present a comprehensive three-phase study to examine (1) the cultural understanding of Large Multimodal Models (LMMs) by introducing DalleStreet, a large-scale dataset generated by DALL-E 3 and validated by humans, containing 9,935 images of 67 co
Externí odkaz:
http://arxiv.org/abs/2407.02067
Existing works examining Vision-Language Models (VLMs) for social biases predominantly focus on a limited set of documented bias associations, such as gender:profession or race:crime. This narrow scope often overlooks a vast range of unexamined impli
Externí odkaz:
http://arxiv.org/abs/2407.02066