Hongyang Du
YOU?
Author Swipe
Tumor necrosis-informed prognostic nomogram for clear cell renal cell carcinoma model development and clinical validation Open
Background This study investigated the prognostic role of tumor necrosis (TN) in non-metastatic clear cell renal cell carcinoma (ccRCC). Methods We enrolled 1,212 non-metastatic ccRCC patients undergoing nephrectomy (2013–2023) in this ret…
View article: Experience Scaling: Post-Deployment Evolution For Large Language Models
Experience Scaling: Post-Deployment Evolution For Large Language Models Open
Scaling model size, training data, and compute power have driven advances in large language models (LLMs), but these approaches are reaching saturation as human-generated text is exhausted and further gains diminish. We propose experience …
View article: Optimizing Split Federated Learning with Unstable Client Participation
Optimizing Split Federated Learning with Unstable Client Participation Open
To enable training of large artificial intelligence (AI) models at the network edge, split federated learning (SFL) has emerged as a promising approach by distributing computation between edge devices and a server. However, while unstable …
View article: Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution
Ubiquitous Intelligence Via Wireless Network-Driven LLMs Evolution Open
We introduce ubiquitous intelligence as a paradigm where Large Language Models (LLMs) evolve within wireless network-driven ecosystems. Unlike static model deployments, this approach enables scalable and continuous intelligence ascension t…
View article: M3LLM: Model Context Protocol-aided Mixture of Vision Experts For Multimodal LLMs in Networks
M3LLM: Model Context Protocol-aided Mixture of Vision Experts For Multimodal LLMs in Networks Open
Current Multimodal Large Language Models (MLLMs) rely on centralized architectures and often suffer from poor alignment between the input task and their fixed visual encoding modules, which limits performance on diverse and dynamic visual …
View article: Joint Association and Phase Shifts Design for UAV-mounted Stacked Intelligent Metasurfaces-assisted Communications
Joint Association and Phase Shifts Design for UAV-mounted Stacked Intelligent Metasurfaces-assisted Communications Open
Stacked intelligent metasurfaces (SIMs) have emerged as a promising technology for realizing wave-domain signal processing, while the fixed SIMs will limit the communication performance of the system compared to the mobile SIMs. In this wo…
View article: Explainable machine learning for predicting distant metastases in renal cell carcinoma patients: a population-based retrospective study
Explainable machine learning for predicting distant metastases in renal cell carcinoma patients: a population-based retrospective study Open
Background Distant metastasis is a key factor contributing to poor prognosis in renal cell carcinoma (RCC). Early prediction of metastasis is crucial for developing personalized treatment plans and improving patient outcomes. This study ai…
View article: Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization
Diffusion-Modeled Reinforcement Learning for Carbon and Risk-Aware Microgrid Optimization Open
This paper introduces DiffCarl, a diffusion-modeled carbon- and risk-aware reinforcement learning algorithm for intelligent operation of multi-microgrid systems. With the growing integration of renewables and increasing system complexity, …
View article: Energy-Efficient RSMA-enabled Low-altitude MEC Optimization Via Generative AI-enhanced Deep Reinforcement Learning
Energy-Efficient RSMA-enabled Low-altitude MEC Optimization Via Generative AI-enhanced Deep Reinforcement Learning Open
The growing demand for low-latency computing in 6G is driving the use of UAV-based low-altitude mobile edge computing (MEC) systems. However, limited spectrum often leads to severe uplink interference among ground terminals (GTs). In this …
View article: MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems
MAD-Spear: A Conformity-Driven Prompt Injection Attack on Multi-Agent Debate Systems Open
Multi-agent debate (MAD) systems leverage collaborative interactions among large language models (LLMs) agents to improve reasoning capabilities. While recent studies have focused on increasing the accuracy and scalability of MAD systems, …
View article: Graph Diffusion-Based AeBS Deployment and Resource Allocation for RSMA-Enabled URLLC Low-Altitude Economy Networks
Graph Diffusion-Based AeBS Deployment and Resource Allocation for RSMA-Enabled URLLC Low-Altitude Economy Networks Open
As a key component of low-altitude economic networks, aerial base stations (AeBSs) provide flexible and reliable wireless coverage to support 6G ultra-reliable and low-latency communication (URLLC) services. However, limited spectrum resou…
View article: How to Design and Train Your Implicit Neural Representation for Video Compression
How to Design and Train Your Implicit Neural Representation for Video Compression Open
Implicit neural representation (INR) methods for video compression have recently achieved visual quality and compression ratios that are competitive with traditional pipelines. However, due to the need for per-sample network training, the …
View article: Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning
Curriculum Learning With Counterfactual Group Relative Policy Advantage For Multi-Agent Reinforcement Learning Open
Multi-agent reinforcement learning (MARL) has achieved strong performance in cooperative adversarial tasks. However, most existing methods typically train agents against fixed opponent strategies and rely on such meta-static difficulty con…
View article: Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception
Wireless Agentic AI with Retrieval-Augmented Multimodal Semantic Perception Open
The rapid development of multimodal AI and Large Language Models (LLMs) has greatly enhanced real-time interaction, decision-making, and collaborative tasks. However, in wireless multi-agent scenarios, limited bandwidth poses significant c…
View article: Context-Aware Semantic Communication for the Wireless Networks
Context-Aware Semantic Communication for the Wireless Networks Open
In next-generation wireless networks, supporting real-time applications such as augmented reality, autonomous driving, and immersive Metaverse services demands stringent constraints on bandwidth, latency, and reliability. Existing semantic…
View article: Empowering Intelligent Low-altitude Economy with Large AI Model Deployment
Empowering Intelligent Low-altitude Economy with Large AI Model Deployment Open
Low-altitude economy (LAE) represents an emerging economic paradigm that redefines commercial and social aerial activities. Large artificial intelligence models (LAIMs) offer transformative potential to further enhance the intelligence of …
View article: Chain-of-Thought for Large Language Model-empowered Wireless Communications
Chain-of-Thought for Large Language Model-empowered Wireless Communications Open
Recent advances in large language models (LLMs) have opened new possibilities for automated reasoning and decision-making in wireless networks. However, applying LLMs to wireless communications presents challenges such as limited capabilit…
View article: Temporal Spectrum Cartography in Low-Altitude Economy Networks: A Generative AI Framework with Multi-Agent Learning
Temporal Spectrum Cartography in Low-Altitude Economy Networks: A Generative AI Framework with Multi-Agent Learning Open
This paper introduces a two-stage generative AI (GenAI) framework tailored for temporal spectrum cartography in low-altitude economy networks (LAENets). LAENets, characterized by diverse aerial devices such as UAVs, rely heavily on wireles…
View article: ReaCritic: Large Reasoning Transformer-based DRL Critic-model Scaling For Heterogeneous Networks
ReaCritic: Large Reasoning Transformer-based DRL Critic-model Scaling For Heterogeneous Networks Open
Heterogeneous Networks (HetNets) pose critical challenges for intelligent management due to the diverse user requirements and time-varying wireless conditions. These factors introduce significant decision complexity, which limits the adapt…
View article: VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations for Synthetic Videos Open
Synthetic video generation using foundation models has gained significant attention due to its realism and broad applications. However, while these models excel at generating visually coherent and high-quality video frames, they often over…
View article: Model Context Protocol-based Internet of Experts For Wireless Environment-aware LLM Agents
Model Context Protocol-based Internet of Experts For Wireless Environment-aware LLM Agents Open
Large Language Models (LLMs) exhibit strong general-purpose reasoning abilities but lack access to wireless environment information due to the absence of native sensory input and domain-specific priors. Previous attempts to apply LLMs in w…
View article: VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding
VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understanding Open
Vision-Language Models (VLMs) have achieved strong results in video understanding, yet a key question remains: do they truly comprehend visual content or only learn shallow correlations between vision and language? Real visual understandin…
View article: Task-Oriented Semantic Communication in Large Multimodal Models-Based Vehicle Networks
Task-Oriented Semantic Communication in Large Multimodal Models-Based Vehicle Networks Open
Task-oriented semantic communication has emerged as a fundamental approach for enhancing performance in various communication scenarios. While recent advances in Generative Artificial Intelligence (GenAI), such as Large Language Models (LL…
View article: Supervised Score-Based Modeling by Gradient Boosting
Supervised Score-Based Modeling by Gradient Boosting Open
Score-based generative models can effectively learn the distribution of data by estimating the gradient of the distribution. Due to the multi-step denoising characteristic, researchers have recently considered combining score-based generat…
View article: Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions
Revolution of Wireless Signal Recognition for 6G: Recent Advances, Challenges and Future Directions Open
Wireless signal recognition (WSR) is a crucial technique for intelligent communications and spectrum sharing in the next six-generation (6G) wireless communication networks. It can be utilized to enhance network performance and efficiency,…
View article: Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences
Large-Scale AI in Telecom: Charting the Roadmap for Innovation, Scalability, and Enhanced Digital Experiences Open
This white paper discusses the role of large-scale AI in the telecommunications industry, with a specific focus on the potential of generative AI to revolutionize network functions and user experiences, especially in the context of 6G syst…
View article: AOLO: Analysis and Optimization For Low-Carbon Oriented Wireless Large Language Model Services
AOLO: Analysis and Optimization For Low-Carbon Oriented Wireless Large Language Model Services Open
Recent advancements in large language models (LLMs) have led to their widespread adoption and large-scale deployment across various domains. However, their environmental impact, particularly during inference, has become a growing concern d…
View article: Relationship of obesity, body fat, benign adrenal tumors and the mediating mechanism: a two-step mendelian randomization study
Relationship of obesity, body fat, benign adrenal tumors and the mediating mechanism: a two-step mendelian randomization study Open
Our study demonstrates that obesity and elevated body fat may serve as risk factors for benign adrenal tumors. Furthermore, we identify the mediating role of total/bioavailable testosterone levels in women, suggesting its potential target …
View article: Generative AI-enabled Wireless Communications for Robust Low-Altitude Economy Networking
Generative AI-enabled Wireless Communications for Robust Low-Altitude Economy Networking Open
Low-Altitude Economy Networks (LAENets) have emerged as significant enablers of social activities, offering low-altitude services such as the transportation of packages, groceries, and medical supplies. Owing to their control mechanisms an…