Zobrazeno 1 - 10
of 42 348
pro vyhledávání: '"Wang,Ping"'
Current efforts to learn scalable policies in robotic manipulation primarily fall into two categories: one focuses on "action," which involves behavior cloning from extensive collections of robotic data, while the other emphasizes "vision," enhancing
Externí odkaz:
http://arxiv.org/abs/2412.15109
Autor:
Yan, Kun, Bouraoui, Zied, Wei, Fangyun, Xu, Chang, Wang, Ping, Jameel, Shoaib, Schockaert, Steven
The aim of multi-label few-shot image classification (ML-FSIC) is to assign semantic labels to images, in settings where only a small number of training examples are available for each label. A key feature of the multi-label setting is that images of
Externí odkaz:
http://arxiv.org/abs/2412.13732
We propose a sequential measurement protocol for accurate low-temperature estimation. The resulting correlated outputs significantly enhance the low temperature precision compared to that of the independent measurement scheme. This enhancement manife
Externí odkaz:
http://arxiv.org/abs/2412.04878
Autor:
Zhang, Delin, Wei, Heshuang, Duan, Jinyu, Chen, Jiali, Yue, Dongdong, Yang, Yuhe, Gou, Jinlong, Yan, Junxin, Zhai, Kun, Wang, Ping, Hu, Shuai, Jia, Zhiyan, Jiang, Wei, Wang, Wenhong, Li, Yue, Jiang, Yong
Efficiently manipulating the magnetization of van der Waals ferromagnets has attracted considerable interest in developing room-temperature two-dimensional material-based memory and logic devices. Here, taking advantage of the unique properties of th
Externí odkaz:
http://arxiv.org/abs/2412.04872
Mental health support in colleges is vital in educating students by offering counseling services and organizing supportive events. However, evaluating its effectiveness faces challenges like data collection difficulties and lack of standardized metri
Externí odkaz:
http://arxiv.org/abs/2412.04326
Autor:
Niknia, Farnaz, Wang, Ping
This paper addresses the challenge of edge caching in dynamic environments, where rising traffic loads strain backhaul links and core networks. We propose a Proximal Policy Optimization (PPO)-based caching strategy that fully incorporates key file at
Externí odkaz:
http://arxiv.org/abs/2411.09812
Mixture-of-Experts (MOE) has recently become the de facto standard in Multi-domain recommendation (MDR) due to its powerful expressive ability. However, such MOE-based method typically employs all experts for each instance, leading to scalability iss
Externí odkaz:
http://arxiv.org/abs/2411.06826
Federated learning (FL) in wireless computing effectively utilizes communication bandwidth, yet it is vulnerable to errors during the analog aggregation process. While removing users with unfavorable channel conditions can mitigate these errors, it a
Externí odkaz:
http://arxiv.org/abs/2411.06721
Glitch tokens in Large Language Models (LLMs) can trigger unpredictable behaviors, threatening model reliability and safety. Existing detection methods rely on predefined patterns, limiting their adaptability across diverse LLM architectures. We prop
Externí odkaz:
http://arxiv.org/abs/2410.15052
The image-based multimodal automatic speech recognition (ASR) model enhances speech recognition performance by incorporating audio-related image. However, some works suggest that introducing image information to model does not help improving ASR perf
Externí odkaz:
http://arxiv.org/abs/2410.00822