Cheng Zeng

Intelligent Question-Answering System and Inference Mechanism for Grid Dispatching with Energy Storage Access Scenarios Based on Semantic Models

Lin Yang, Fan Yang, Feng Yongqing, Cheng Zeng et autres

INTRODUCTION: In the power grid energy storage dispatch system, after the large-scale integration of new energy storage systems, the demand for inquiries regarding the operation and maintenance of storage equipment as well as the coordinated power regulation has significantly increased. The intelligent …

cn (code pays fourni par la source)

Population ageing and digital finance: New evidence from China

Shixiang Cao, Zhigang Qiu, Xingmei Xu, Cheng Zeng

cn (code pays fourni par la source)

Multimodal Interest-Shifting Sequence Recommendation with Offline Policy Optimization and Drift-Aware Representation Learning

Changcheng Shao, Cheng Zeng, Xiaogang Ye, Lili Chen et autres

Interest changes complicate sequential recommendation when interaction histories are combined with item content. We evaluate MM-DRLSR on four public Amazon and Yelp benchmarks. The model integrates category-overlap drift supervision, history-derived drift representations, lightweight identifier–image–text fusion, candidate-conditioned scoring, and an offline actor–critic surrogate …

cn (code pays fourni par la source)

Multi-Task LSTM-Attention with Adaptive Isolation Forest for Intelligent Project Implementation Monitoring

Xiaocong Ruan, Yue Wang, Rixi Mo, Changcheng Shao et autres

Abstract Manual oversight of funded research projects does not scale. Progress delays, budget irregularities, and superficial reportingoften go undetected until final acceptance, while existing detection methods struggle to distinguish legitimate scheduleadjustments from genuine anomalies. We present the Intelligent Project Monitoring System (IPMS), …

cn (code pays fourni par la source)

Gromov Hyperbolicity of Substitution graphs

Qingcheng Zeng, Cheng Zeng, Yumei Xue, Huixia He

In this paper, we construct a class of infinite graphs, called substitution graphs. The vertex set consists of all finite words over a finite alphabet. A directed graph is formed by adding vertical edges connecting each word to its children and horizontal …

Abelian maximal pattern complexity of two-dimensional words

Qingcheng Zeng, Yumei Xue, Cheng Zeng

In this paper, we study the maximal pattern complexity of two-dimensional words up to Abelian equivalence. We establish a lower bound for the Abelian maximal pattern complexity of two-dimensional words that are non-doubly periodic by projection under the existence of a transverse …

Gradient-guided layerwise adaptive noise injection for pre-trained language model fine-tuning

Qinglin Jiang, Cheng Zeng, Nan Chi

Fine-tuning pre-trained language models (PLMs) is crucial for achieving performance gains in downstream natural language processing tasks, but it is prone to overfitting in low-resource scenarios. Existing noise-based regularization methods typically rely on static parameter statistics or predefined heuristics to mitigate this …

cn (code pays fourni par la source)

Human-Machine Collaborative Visual Orchestration Technology for AI-Assisted Dispatch Document Generation

Hongshan Chen, Lin Yang, Fangdi Hou, Cheng Zeng et autres

The current power dispatching field faces challenges such as low utilization of knowledge documents, insufficient efficiency in manual generation and processing, and a lack of efficient visual collaboration tools, which restrict the efficiency of dispatching work and the realization of the value …

cn (code pays fourni par la source)

CoMFE-YOLOv5: Coordinate Multi-Branch Feature Enhancement YOLOv5 for small object detection in UAVs

Zhihao Xu, Cheng Zeng, Y C Pan, Anzheng Tang et autres

cn (code pays fourni par la source)

Energy-Efficient Resource Management for MEC-Assisted VR Systems: A D3QN-IL Approach

Na Su, Jun-Bo Wang, Anzheng Tang, Cheng Zeng et autres

cn, hk, se (code pays fourni par la source)

Gradient-Guided Layerwise Adaptive Noise Injection for Pre-trained Language Model Fine-tuning

Qinglin Jiang, Cheng Zeng, Nan Chi

cn (code pays fourni par la source)

Animator-Centric Skeleton Generation on Objects with Fine-Grained Details

Mingze Sun, Cheng Zeng, Jiansong Pei, Junhao Chen et autres

Skeleton generation is essential for animating 3D assets, but current deep learning methods remain limited: they cannot handle the growing structural complexity of modern models and offer minimal controllability, creating a major bottleneck for real-world animation workflows. To address this, we propose …