Yuxuan Cai

Driving Trajectory of Electricity Spot Market Pilot Policy in China’s Renewable Energy Development: Quasi-Experimental Evidence with Industrial Structure Moderation

Yuxuan Cai, Feiyang Zhao, Tao Zhang, Xi Wang et autres

With the rapid growth of installed capacity for renewable energy in recent years, the challenge of developing renewable electricity has become increasingly significant. Reforms in the electricity market have played a crucial role in facilitating the large-scale absorption of renewable energy. This …

mo, hk (code pays fourni par la source)

AutoMem: A Text-Gradient Recursive Self-Improvement Framework for Automated Memory Architectures Search

Lin Du, Jie Zhou, Yuxuan Cai, Kai Chen et autres

Long-term memory is increasingly central to LLM agents, yet memory design remains a highly coupled architecture problem: what to encode, how to store it, how to retrieve it, and how to manage it can vary substantially across tasks and backbone models. We …

Cooperative Tracking Control Combining with Reinforcement Learning for Heavy-Haul Trains

Yuxuan Cai, Zhaosheng Qiu, Xiaoyong Zhang

It is essential to ensure the consistency of the cooperative control of heavy-haul train to improve the operational efficiency and safety. Nevertheless, the dynamic environment of heavy-haul train brings the challenge for the stability of cooperative control. In this paper, a tracking …

gb, cn (code pays fourni par la source)

Impact of intraoperative explanation combined with surgical video review on anatomy learning in laparoscopic distal gastrectomy

Yumei Ding, Xin Liu, Yuxuan Cai, Fangyuan Cheng et autres

OBJECTIVE: To investigate the educational value of combining intraoperative explanations with laparoscopic surgical video reviews for teaching the local anatomy of the stomach. METHODS: Thirty resident physicians undergoing standardised training in our hospital, including undergraduate resident physicians and clinical-type postgraduates in surgery …

hk, cn (code pays fourni par la source)

UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions

Zhucun Xue, Jiangning Zhang, Teng Hu, Haoyang He et autres

The quality of the video dataset (image quality, resolution, and fine-grained caption) greatly influences the performance of the video generation model. The growing demand for video applications sets higher requirements for high-quality video generation models. For example, the generation of movie-level Ultra-High …

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

Haoyang He, Jiangning Zhang, Yuxuan Cai, Hongxu Chen et autres

Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities, are limited by quadratic computational complexity in high-resolution scenarios. Recently, state-space …

cn (code pays fourni par la source)

Task-Core Memory Management and Consolidation for Long-term Continual Learning

Tianyu Huai, Jie Zhou, Yuxuan Cai, Qin Chen et autres

In this paper, we focus on a long-term continual learning (CL) task, where a model learns sequentially from a stream of vast tasks over time, acquiring new knowledge while retaining previously learned information in a manner akin to human learning. Unlike traditional …

Clean energy development and low-carbon transition in China’s power industry

Yuxuan Cai, Edmund HoiNgan Loi, Chih-Lin Tung, Hao Wang et autres

Introduction China is the largest emitter of carbon dioxide (CO2) in the world, with its power industry being the primary source of these emissions. The high emission levels are primarily attributed to the extensive consumption of fossil resources during thermal power generation. …

mo (code pays fourni par la source)

Zephyr: A High-Performance Framework for Graph Attention Networks on Heterogeneous Data

Wenxiu Ding, Yuxuan Cai, Mingxin Chen, Zheng Yan et autres

The Graph Attention Network (GAT), based on the foundational principles of Graph Neural Network (GNN), represents a significant advancement in the accurate representation and in-depth understanding of complex data structures. However, GAT can’t proficiently handle heterogeneous data, which negatively affects model performance. …

cn (code pays fourni par la source)

Control backbone detection in omnigenic disease neighborhood targeting core module

Yuxuan Cai, Bingbo Wang, Junru Zheng

cn (code pays fourni par la source)

MobileMamba: Lightweight Multi-Receptive Visual Mamba Network

Haoyang He, Jiangning Zhang, Yuxuan Cai, Hongxu Chen et autres

Previous research on lightweight models has primarily focused on CNNs and Transformer-based designs. CNNs, with their local receptive fields, struggle to capture long-range dependencies, while Transformers, despite their global modeling capabilities, are limited by quadratic computational complexity in high-resolution scenarios. Recently, state-space …

SecFed: A Secure and Efficient Federated Learning Based on Multi-Key Homomorphic Encryption

Yuxuan Cai, Wenxiu Ding, Yuxuan Xiao, Zheng Yan et autres

Federated Learning (FL) is widely used in various industries because it effectively addresses the predicament of isolated data island. However, eavesdroppers is capable of inferring user privacy from the gradients or models transmitted in FL. Homomorphic Encryption (HE) can be applied in …

cn (code pays fourni par la source)