Zobrazeno 1 - 10
of 45 139
pro vyhledávání: '"li, Tao"'
Numerous real-world systems, including manufacturing processes, supply chains, and robotic systems, involve multiple independent entities with diverse objectives. The potential for conflicts arises from the inability of these entities to accurately p
Externí odkaz:
http://arxiv.org/abs/2411.01918
Autor:
Wen, Dong, Liu, Zhongpei, Yang, Tong, Li, Tao, Li, Tianyun, Li, Chenglong, Li, Jie, Sun, Zhigang
Neural-networks-driven intelligent data-plane (NN-driven IDP) is becoming an emerging topic for excellent accuracy and high performance. Meanwhile we argue that NN-driven IDP should satisfy three design goals: the flexibility to support various NNs m
Externí odkaz:
http://arxiv.org/abs/2411.00408
Quantum secret sharing (QSS) plays a pivotal role in multiparty quantum communication, ensuring the secure distribution of private information among multiple parties. However, the security of QSS schemes can be compromised by attacks exploiting imper
Externí odkaz:
http://arxiv.org/abs/2410.23562
Social network platforms (SNP), such as X and TikTok, rely heavily on user-generated content to attract users and advertisers, yet they have limited control over content provision, which leads to the proliferation of misinformation across platforms.
Externí odkaz:
http://arxiv.org/abs/2411.00825
Text detoxification, a variant of style transfer tasks, finds useful applications in online social media. This work presents a fine-tuning method that only uses non-parallel data to turn large language models (LLM) into a detoxification rewritter. We
Externí odkaz:
http://arxiv.org/abs/2410.20298
Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al.,2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024) are shown to
Externí odkaz:
http://arxiv.org/abs/2410.16710
Federated learning (FL) is susceptible to a range of security threats. Although various defense mechanisms have been proposed, they are typically non-adaptive and tailored to specific types of attacks, leaving them insufficient in the face of multipl
Externí odkaz:
http://arxiv.org/abs/2410.17431
Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. However, the diversity of downstream tasks and practical requirements makes deploying multiple full-parameter fine-tuned models challeng
Externí odkaz:
http://arxiv.org/abs/2410.08666
Autor:
Song, Wange, Liu, Xuanyu, Sun, Jiacheng, You, Oubo, Wu, Shengjie, Chen, Chen, Zhu, Shining, Li, Tao, Zhang, Shuang
The non-Abelian braiding describes the exchange behavior of anyons, which can be leveraged to encode qubits for quantum computing. Recently, this concept has been realized in classical photonic and acoustic systems. However, these implementations are
Externí odkaz:
http://arxiv.org/abs/2410.06461
Autor:
Huang, Zhehao, Cheng, Xinwen, Zheng, JingHao, Wang, Haoran, He, Zhengbao, Li, Tao, Huang, Xiaolin
Machine unlearning (MU) has emerged to enhance the privacy and trustworthiness of deep neural networks. Approximate MU is a practical method for large-scale models. Our investigation into approximate MU starts with identifying the steepest descent di
Externí odkaz:
http://arxiv.org/abs/2409.19732