Yu Wang
YOU?
Author Swipe
View article: CityLight: A Neighborhood-inclusive Universal Model for Coordinated City-scale Traffic Signal Control
CityLight: A Neighborhood-inclusive Universal Model for Coordinated City-scale Traffic Signal Control Open
View article: Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs
Fighting Fire with Fire (F3): A Training-free and Efficient Visual Adversarial Example Purification Method in LVLMs Open
View article: DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models Open
View article: DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation
DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation Open
View article: REACT3D: Real-time Edge Accelerator for Incremental Training in 3D Gaussian Splatting based SLAM Systems
REACT3D: Real-time Edge Accelerator for Incremental Training in 3D Gaussian Splatting based SLAM Systems Open
View article: Hierarchical Reinforcement Learning-Based Multi-UAV Cooperative Navigation Method
Hierarchical Reinforcement Learning-Based Multi-UAV Cooperative Navigation Method Open
To address the multi-UAV multi-target allocation and cooperative navigation problem in complex obstacle environments, this paper proposes a navigation method based on hierarchical reinforcement learning. Specifically, the cooperative navig…
View article: Towards Floating Point-Based AI Acceleration: Hybrid PIM with Non-Uniform Data Format and Reduced Multiplications
Towards Floating Point-Based AI Acceleration: Hybrid PIM with Non-Uniform Data Format and Reduced Multiplications Open
Neural networks (NNs) have exhibited excellent performance in various fields of artificial intelligence. However, the primary operations in these mainstream models, including matrix-vector multiplication (MVM), element-wise multiplication …
View article: Identification of Control Parameters in Doubly Fed Induction Generators via Adaptive Differential Evolution
Identification of Control Parameters in Doubly Fed Induction Generators via Adaptive Differential Evolution Open
With the increasing penetration of renewable energy generation, analysis of the transient characteristics of doubly fed induction generators, as the mainstream wind turbine configuration, is made highly significant both theoretically and p…
View article: Efficient Target Assignment via Binarized SHP Path Planning and Plasticity-Aware RL in Urban Adversarial Scenarios
Efficient Target Assignment via Binarized SHP Path Planning and Plasticity-Aware RL in Urban Adversarial Scenarios Open
Accurate and feasible target assignment in an urban environment without road networks remains challenging. Existing methods exhibit critical limitations: computational inefficiency preventing real-time decision-making requirements and poor…
View article: Relationship between cortical activation and sleep quality in cerebral small vessel disease patients: a functional near-infrared spectroscopy (fNIRS) study
Relationship between cortical activation and sleep quality in cerebral small vessel disease patients: a functional near-infrared spectroscopy (fNIRS) study Open
Background Sleep disturbance is common in patients with cerebral small vessel disease (CSVD). The impact of insomnia on cortical activation in CSVD patients and its association with sleep quality remains unclear. Our study used functional …
View article: LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation
LRQ-DiT: Log-Rotation Post-Training Quantization of Diffusion Transformers for Image and Video Generation Open
Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image and text-to-video generation. However, their high computational cost and large parameter sizes pose significant challenges for usage in resource-constraine…
View article: Optimizing resource allocation in industrial IoT with federated machine learning and edge computing integration
Optimizing resource allocation in industrial IoT with federated machine learning and edge computing integration Open
View article: Bio-inspired designing and fabricating hydrophobic functional surface for advanced fuel cell applications: A review
Bio-inspired designing and fabricating hydrophobic functional surface for advanced fuel cell applications: A review Open
View article: Optimizing piezoelectric actuator placement for enhanced vibration control using genetic algorithms
Optimizing piezoelectric actuator placement for enhanced vibration control using genetic algorithms Open
Active vibration control in flexible structures remains a critical challenge in engineering applications. This study proposes an optimization framework for piezoelectric sensor and actuator configurations in cantilever beams using a geneti…
View article: Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning
Online Planning for Multi-UAV Pursuit-Evasion in Unknown Environments Using Deep Reinforcement Learning Open
View article: IDEA-GP: Instruction-Driven Architecture with Efficient Online Workload Allocation for Geometric Perception
IDEA-GP: Instruction-Driven Architecture with Efficient Online Workload Allocation for Geometric Perception Open
View article: What Matters in Learning a Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study
What Matters in Learning a Zero-Shot Sim-to-Real RL Policy for Quadrotor Control? A Comprehensive Study Open
View article: R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing Open
Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled Small Language Models (SLMs) significantly enhance efficienc…
View article: Optimization of crop planting strategies: an integrated scheme of linear programming and intelligent optimization algorithms
Optimization of crop planting strategies: an integrated scheme of linear programming and intelligent optimization algorithms Open
To address the challenge of developing optimal planting strategies for multiple crops under the constraints of diverse greenhouse conditions and various types of cultivated land, a crop planting strategy based on intelligent optimization a…
View article: An artificial intelligence-based limited area model for forecasting of surface meteorological variables
An artificial intelligence-based limited area model for forecasting of surface meteorological variables Open
Artificial intelligence-based models for global weather forecasting have advanced rapidly, but research on high-resolution data-driven limited area models remains scarce. Here we introduce a limited area artificial intelligence-based weath…
View article: Ti-diffused KTN waveguide enabling intensity modulation based on the quadratic electro-optic effect
Ti-diffused KTN waveguide enabling intensity modulation based on the quadratic electro-optic effect Open
Optical waveguides are fundamental components in integrated optics, enabling the confinement of light beams at micron and nanometer scales. The performance of electro-optic materials is the key to realizing waveguide-based modulation devic…
View article: AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms Open
View article: A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation
A Non-Invasive Load Monitoring Method for Edge Computing Based on MobileNetV3 and Dynamic Time Regulation Open
In recent years, non-intrusive load monitoring (NILM) technology has attracted much attention in the related research field by virtue of its unique advantage of utilizing single meter data to achieve accurate decomposition of device-level …
View article: Observer-Based Prescribed-Time Bipartite Output Consensus of Nonlinear Multi-Agent Systems with Exogenous Disturbances
Observer-Based Prescribed-Time Bipartite Output Consensus of Nonlinear Multi-Agent Systems with Exogenous Disturbances Open
In this study, we developed a framework for achieving prescribed-time bipartite output consensus in nonlinear multi-agent systems by introducing a distributed observer approach. We propose a novel control protocol that utilizes a bipartite…
View article: AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms
AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms Open
The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms. The Challenge c…
View article: FlightVGM: Efficient Video Generation Model Inference with Online Sparsification and Hybrid Precision on FPGAs
FlightVGM: Efficient Video Generation Model Inference with Online Sparsification and Hybrid Precision on FPGAs Open
View article: FMC-LLM: Enabling FPGAs for Efficient Batched Decoding of 70B+ LLMs with a Memory-Centric Streaming Architecture
FMC-LLM: Enabling FPGAs for Efficient Batched Decoding of 70B+ LLMs with a Memory-Centric Streaming Architecture Open
View article: The effect of physical activities on internet addiction in college students: the mediating effect of self-control
The effect of physical activities on internet addiction in college students: the mediating effect of self-control Open
Objective To investigate the relationship between college students' physical activities and Internet addiction, to investigate the role self-control control plays in this relationship, and to provide a theoretical foundation for the allevi…
View article: Sampled-data self-learning observer based attitude tracking control against sensor-actuator faults
Sampled-data self-learning observer based attitude tracking control against sensor-actuator faults Open
This paper proposes an intermittent measurement-based attitude tracking control strategy for spacecraft operating in the presence of sensor-actuator faults. A sampled-data (self-)learning observer is developed to estimate both the spacecra…
View article: Mineralogical and geochemical characteristics of the third member of Palaeogene Dongying formation in the Nanpu Sag, Bohai Bay Basin: implications for controlling on organic matter accumulation
Mineralogical and geochemical characteristics of the third member of Palaeogene Dongying formation in the Nanpu Sag, Bohai Bay Basin: implications for controlling on organic matter accumulation Open
Introduction and Methods To identify the unconventional shale oil exploration potential of the third member of the Palaeogene Dongying Formation (Ed 3 ) in the Nanpu Sag, Bohai Bay Basin, variations in paleoclimate and paleoenvironment and…