Yong Zhang

ArtGDance: music-driven 3D group dance generation framework

Yong Zhang, Rufeng Duan, Haifeng Yu, Kaixing Yang

hk, cn (code pays fourni par la source)

Modality-task dependent heterogeneous mixture-of-experts model for multimodal time series representation learning

Lei Yao, Yong Zhang, Qin Li, Qi Li et autres

Multimodal time series representation learning has been extensively applied in healthcare, financial forecasting, and autonomous driving. However, heterogeneity among modalities has challenges for robust representation learning and multimodal task adaptation. To address the limitations of existing methods that lack sufficient consideration of …

cn (code pays fourni par la source)

Fine-grained inter-series dependency enhanced mining for multi-domain multivariate time series forecasts

Qi Li, Tianmu Sha, Chenyang He, Zhenyu Zhang et autres

Multi-domain multivariate time series (MTS) forecasting is increasingly important for large-scale and transferable time-series modeling. However, heterogeneous datasets usually contain different numbers of variables, making scalable inter-series dependency modeling challenging. Existing scalable forecasting paradigms often rely on channel-independent (CI) strategies to accommodate …

cn (code pays fourni par la source)

Leveraging AI-based organizational learning for sustainable performance in manufacturing

Mingxuan Wang, Rixiao Cui, Xiaohui Zhao, Yong Zhang et autres

Purpose The growing integration of artificial intelligence (AI) into manufacturing has intensified interest in its implications for sustainability. This study examines how AI-based organizational learning (AIOL) affects sustainable performance (SP) in manufacturing firms and investigates the mediating roles of three dimensions of …

cn (code pays fourni par la source)

Performance assessment and multi-scale mechanisms of a bio-based dust suppressant incorporated with carboxymethyl guar gum

Xiaonan Wang, Yue Hu, Yong Zhang, Yongjie Shi et autres

cn (code pays fourni par la source)

Orchestrating Generative AI Services in Ultra-Dense 6G Networks: A Mean Field Game Framework

Yuhao Chai, Zideng Feng, Zhenyu Zhang, Yinglei Teng et autres

cn (code pays fourni par la source)

Dynamic Refrigeration Performances of a Large Cooling System in China

Bo Ma, Wei Chen, Yong Zhang, Yongzhi Lei et autres

Cooling energy consumption constitutes a significant portion of global primary energy usage, highlighting the need to optimize cooling demands and address inefficiencies in large refrigeration systems. This study examines the dynamic operation of a full‐scale industrial cooling system in Northeastern China, based …

cn (code pays fourni par la source)

Reinforcement learning-driven net order selection for efficient analog IC routing

Yong Zhang, Wenjie Li, Guangjun Ge, Jin-Qiao Wang et autres

The A∗ algorithm is one of the most common analog integrated circuit (IC) routing techniques. As the number of nets increases, the routing order of this heuristic routing algorithm will affect the routing results immensely. Currently, artificial intelligence (AI) technologies are widely …

Shallow resource foraging and deep-water shift: plant-soil feedbacks sustain transient coexistence during Phyllostachys edulis invasion

Ziqiang Liu, Wei Liu, Yong Zhang, Jiang Jiang et autres

• Stable isotopes and niche overlap detect P. edulis effects on broad-leaved forests. • P. edulis mostly takes up shallow, nutrient-rich water via its well-developed root. • Q. acutissima shifts water uptake from shallow to deep soil due to P. edulis invasion. …

cn (code pays fourni par la source)

MAML-SAMIoT: A cloud-fog computing and MAML-based few-shot IoT intrusion detection model

Yong Zhang, Yue Wu, Shaoyu Zhao, Zhenpeng Liu

cn (code pays fourni par la source)

Research on cigarette packaging strategy based on Kansei engineering and decision tree

Yuwen Shao, Yong Zhang, Junsong Zhang, Shaodong Hu et autres

To accurately quantify consumer emotional needs and visual preferences in cigarette packaging design, and address the subjective and imprecise limitations of traditional design decision-making methods, this study integrates Kansei Engineering with Decision Tree. By utilizing web crawlers, 2360 consumer reviews from 2018 …

cn (code pays fourni par la source)

RAM++: Robust Representation Learning via Adaptive Mask for All-in-One Image Restoration

Zilong Zhang, Chuwei Qin, Chunle Guo, Yong Zhang et autres

This work presents Robust Representation Learning via Adaptive Mask (RAM++), a two-stage framework for all-in-one image restoration. RAM++ integrates high-level semantic understanding with low-level texture generation to achieve content-oriented robust restoration. It addresses the limitations of existing degradation-oriented methods in extreme scenarios …