Zobrazeno 1 - 10
of 187
pro vyhledávání: '"Li, Yinchuan"'
Autor:
Li, Xin-Chun, Song, Shaoming, Li, Yinchuan, Li, Bingshuai, Shao, Yunfeng, Yang, Yang, Zhan, De-Chuan
In some real-world applications, data samples are usually distributed on local devices, where federated learning (FL) techniques are proposed to coordinate decentralized clients without directly sharing users' private data. FL commonly follows the pa
Externí odkaz:
http://arxiv.org/abs/2404.09232
Parameter-efficient fine-tuning stands as the standard for efficiently fine-tuning large language and vision models on downstream tasks. Specifically, the efficiency of low-rank adaptation has facilitated the creation and sharing of hundreds of custo
Externí odkaz:
http://arxiv.org/abs/2402.15414
Millimeter-Wave Massive MIMO is important for beyond 5G or 6G wireless communication networks. The goal of this paper is to establish successful communication between the cellular base stations and devices, focusing on the problem of joint user activ
Externí odkaz:
http://arxiv.org/abs/2402.04704
State-of-the-art large language models (LLMs) are commonly deployed as online services, necessitating users to transmit informative prompts to cloud servers, thus engendering substantial privacy concerns. In response, we present ConfusionPrompt, a no
Externí odkaz:
http://arxiv.org/abs/2401.00870
GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward. We contribute to relaxing hypotheses limiting the application range of
Externí odkaz:
http://arxiv.org/abs/2312.15246
Autor:
Zhu, Didi, Li, Zexi, Zhang, Min, Yuan, Junkun, Shao, Yunfeng, Liu, Jiashuo, Kuang, Kun, Li, Yinchuan, Wu, Chao
Large-scale vision-language (V-L) models have demonstrated remarkable generalization capabilities for downstream tasks through prompt tuning. However, the mechanisms behind the learned text representations are unknown, limiting further generalization
Externí odkaz:
http://arxiv.org/abs/2306.15955
Multi-task reinforcement learning and meta-reinforcement learning have been developed to quickly adapt to new tasks, but they tend to focus on tasks with higher rewards and more frequent occurrences, leading to poor performance on tasks with sparse r
Externí odkaz:
http://arxiv.org/abs/2306.09742
We propose the GFlowNets with Human Feedback (GFlowHF) framework to improve the exploration ability when training AI models. For tasks where the reward is unknown, we fit the reward function through human evaluations on different trajectories. The go
Externí odkaz:
http://arxiv.org/abs/2305.07036
Autor:
Zhu, Didi, Li, Yinchuan, Shao, Yunfeng, Hao, Jianye, Wu, Fei, Kuang, Kun, Xiao, Jun, Wu, Chao
We introduce a new problem in unsupervised domain adaptation, termed as Generalized Universal Domain Adaptation (GUDA), which aims to achieve precise prediction of all target labels including unknown categories. GUDA bridges the gap between label dis
Externí odkaz:
http://arxiv.org/abs/2305.04466
Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algori
Externí odkaz:
http://arxiv.org/abs/2304.11989