Ye Ouyang
YOU?
Author Swipe
View article: FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning
FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning Open
Text-to-Image (T2I) models have demonstrated their versatility in a wide range of applications. However, adaptation of T2I models to specialized tasks is often limited by the availability of task-specific data due to privacy concerns. On t…
View article: Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies
Leveraging AI Agents for Autonomous Networks: A Reference Architecture and Empirical Studies Open
The evolution toward Level 4 (L4) Autonomous Networks (AN) represents a strategic inflection point in telecommunications, where networks must transcend reactive automation to achieve genuine cognitive capabilities--fulfilling TM Forum's vi…
View article: UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization Open
Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we introduce UrbanMind, a tool-enhanced retrieval-augmented gener…
View article: LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps
LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps Open
Large language models (LLMs) have opened new opportunities for automated mobile app exploration, an important and challenging problem that used to suffer from the difficulty of generating meaningful UI interactions. However, existing LLM-b…
View article: Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks
Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks Open
Large language models (LLMs) have demonstrated remarkable capabilities, but they require vast amounts of data and computational resources. In contrast, smaller models (SMs), while less powerful, can be more efficient and tailored to specif…
View article: Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion
Contrastive Private Data Synthesis via Weighted Multi-PLM Fusion Open
Substantial quantity and high quality are the golden rules of making a good training dataset with sample privacy protection equally important. Generating synthetic samples that resemble high-quality private data while ensuring Differential…
View article: Vertical Federated Learning: Concepts, Advances, and Challenges
Vertical Federated Learning: Concepts, Advances, and Challenges Open
Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters. Motivat…
View article: Physiological roles of human interleukin‐17 family
Physiological roles of human interleukin‐17 family Open
Interleukin‐17 s (IL‐17s) are well‐known proinflammatory cytokines, and their antagonists perform excellently in the treatment of inflammatory skin diseases such as psoriasis. However, their physiological functions have not been given suff…
View article: AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments Open
Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different con…
View article: The effects and predictive value of calcium and magnesium concentrations on nutritional improvement, inflammatory response and diagnosis in patients with Crohn's disease
The effects and predictive value of calcium and magnesium concentrations on nutritional improvement, inflammatory response and diagnosis in patients with Crohn's disease Open
Background Crohn's disease (CD) is a progressive inflammatory disease of the gastrointestinal tract associated with malnutrition, high levels of inflammation and calcium and magnesium deficiencies. However, the relationships between these …
View article: AIGC Empowering Telecom Sector White Paper_chinese
AIGC Empowering Telecom Sector White Paper_chinese Open
In the global craze of GPT, people have deeply realized that AI, as a transformative technology and key force in economic and social development, will bring great leaps and breakthroughs to the global industry and profoundly influence the …
View article: 6G Network Business Support System
6G Network Business Support System Open
6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network …
View article: 6G Network Operation Support System
6G Network Operation Support System Open
6G is the next-generation intelligent and integrated digital information infrastructure, characterized by ubiquitous interconnection, native intelligence, multi-dimensional perception, global coverage, green and low-carbon, native network …
View article: Case Report: Long-term survival of a patient with advanced rectal cancer and multiple pelvic recurrences after seven surgeries
Case Report: Long-term survival of a patient with advanced rectal cancer and multiple pelvic recurrences after seven surgeries Open
Background Rectal cancer has a high risk of recurrence and metastasis, with median survival ranging from 24 months to 36 months. K-RAS mutation is a predictor of poor prognosis in rectal cancer. Advanced rectal cancer can be stopped in its…
View article: AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments
AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments Open
Deep learning models are increasingly deployed to edge devices for real-time applications. To ensure stable service quality across diverse edge environments, it is highly desirable to generate tailored model architectures for different con…
View article: ILC3s restrict the dissemination of intestinal bacteria to safeguard liver regeneration after surgery
ILC3s restrict the dissemination of intestinal bacteria to safeguard liver regeneration after surgery Open
It is generally believed that environmental or cutaneous bacteria are the main origin of surgical infections. Therefore, measures to prevent postoperative infections focus on optimizing hygiene and improving asepsis and antisepsis. In a la…
View article: Vertical Federated Learning: Concepts, Advances and Challenges
Vertical Federated Learning: Concepts, Advances and Challenges Open
Vertical Federated Learning (VFL) is a federated learning setting where multiple parties with different features about the same set of users jointly train machine learning models without exposing their raw data or model parameters. Motivat…
View article: Reinforcement Learning in Computing and Network Convergence Orchestration
Reinforcement Learning in Computing and Network Convergence Orchestration Open
As computing power is becoming the core productivity of the digital economy era, the concept of Computing and Network Convergence (CNC), under which network and computing resources can be dynamically scheduled and allocated according to us…
View article: Network anomaly detection based on keyword embedding log
Network anomaly detection based on keyword embedding log Open
Log anomaly detection is an important and challenging task in the field of Artificial Intelligence for IT Operations (AIOps). Logs that record important runtime information are widely used for troubleshooting purposes. There have been many…
View article: Coupling Heat Conduction and Radiation by an Isogeometric Boundary Element Method in 2-D Structures
Coupling Heat Conduction and Radiation by an Isogeometric Boundary Element Method in 2-D Structures Open
We propose an efficient isogeometric boundary element method to address the coupling of heat conduction and radiation in homogeneous or inhomogeneous materials. The isogeometric boundary element method is used to construct irregular 2D mod…
View article: Next Decade of Telecommunications Artificial Intelligence
Next Decade of Telecommunications Artificial Intelligence Open
It has been an exciting journey since the mobile communications and artificial intelligence were conceived 37 years and 64 years ago. While both fields evolved independently and profoundly changed communications and computing industries, t…
View article: Towards Efficient Communications in Federated Learning: A Contemporary Survey
Towards Efficient Communications in Federated Learning: A Contemporary Survey Open
In the traditional distributed machine learning scenario, the user's private data is transmitted between clients and a central server, which results in significant potential privacy risks. In order to balance the issues of data privacy and…
View article: 4G 5G Cell-level Multi-indicator Forecasting based on Dense-MLP
4G 5G Cell-level Multi-indicator Forecasting based on Dense-MLP Open
With the development of 4G/5G, the rapid growth of traffic has caused a large number of cell indicators to exceed the warning threshold, and network quality has deteriorated. It is necessary for operators to solve the congestion in advance…
View article: 4G/5G Cell-level multi-indicator forecasting based on dense-MLP
4G/5G Cell-level multi-indicator forecasting based on dense-MLP Open
With the development of 4G/5G, the rapid growth of traffic has caused a large number of cell indicators to exceed the warning threshold, and network quality has deteriorated. It is necessary for operators to solve the congestion in advance…
View article: Research on network cloud equipment anomaly and root cause analysis
Research on network cloud equipment anomaly and root cause analysis Open
With the development of 5G communication technology, a cloud computing system has become a trend. However, with the expansion of the scale of deployment and the increase in framework complexity, ensuring the security and stability of cloud…
View article: Real-time detection of UAV detection image of power line insulator bursting based on YOLOV3
Real-time detection of UAV detection image of power line insulator bursting based on YOLOV3 Open
The insulator fault of high voltage line is the main factor of transmission accidents, so positioning and detection of burst insulator of power line has become an important part of routine detection. Traditional UAV detection is still main…
View article: Latent Clustering Models for Outlier Identification in Telecom Data
Latent Clustering Models for Outlier Identification in Telecom Data Open
Collected telecom data traffic has boomed in recent years, due to the development of 4G mobile devices and other similar high-speed machines. The ability to quickly identify unexpected traffic data in this stream is critical for mobile car…