- Beam Squint Effect: a Friend or a Foe in Physical Layer Authentication for RIS-assisted Systems?
- Edge-Computing Framework for Human-Robot Collaboration in Industry 5.0: Enhancing Operator Well-Being and Efficiency in Manufacturing
- A Novel Assessment and Optimization Method of 6G Distributed Network Topology Resilience Based on Groupwise Collaborative Algorithm
- DH-Set: Improving Vision-Language Alignment with Diverse and Hybrid Set-Embeddings Learning
- Move-in-2D: 2D-Conditioned Human Motion Generation
- Research on Testing and Porting of Autonomous and Controllable Digital Information Systems
- Modulation Schemes for an Isolated Active Clamp Boost PFC Converter
- A Study on Predicting Ship Hull Structural Responses in Collisions Based on Machine Learning
- 4Deform: Neural Surface Deformation for Robust Shape Interpolation
- From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
- A Hybrid CNN-LSTM-Transformer Model for IoT Networks Anomaly Detection
- Multi-party Collaborative Attention Control for Image Customization
- dFLMoE: Decentralized Federated Learning via Mixture of Experts for Medical Data Analysis
- Just Dance with π! A Poly-modal Inductor for Weakly-supervised Video Anomaly Detection
- Language Guided Helmet Object Detection
- Analytical and Experimental Study of Giant Magnetostrictive Material on Output Performance for Giant Magnetostrictive Actuator
- Learning from Streaming Video with Orthogonal Gradients
- A Simple Data Augmentation for Feature Distribution Skewed Federated Learning
- Cascaded Control System for a Three-Level Boost Converter of Multi-String PV Inverter
- Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks
- Adv-Cpg: A Customized Portrait Generation Framework with Facial Adversarial Attacks
- Multivariate Template Attack against NTT-based Polynomial Multiplication of Dilithium
- Autoregressive Distillation of Diffusion Transformers
- D 3 -Human: Dynamic Disentangled Digital Human from Monocular Video
- Point Cloud Registration Algorithm Based on Improved Teaching-Learning-Based Optimization with Physics-Inspired Objective Function
- VladVA: Discriminative Fine-tuning of LVLMs
- Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
- A Multitasking Layered Nonlinear Metastructure With Polarization Conversion and Multi-physical Quantities Detection
- DarkIR: Robust Low-Light Image Restoration
- HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition
- FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering
- Practical Decoding for Deep Polar Codes
- LoCoRe: Image Re-Ranking with Long-Context Sequence Modeling
- ADD: Attribution-Driven Data Augmentation Framework for Boosting Image Super-Resolution
- High-Speed Camera Observation of a Cloud-to-ground Flash from a Tropical Thunderstorm
- Single-Objective Optimization Based on 0-1 Programming
- Localizing Events in Videos with Multimodal Queries
- Detecting Adversarial Data Using Perturbation Forgery
- Assessing Creativity and Risk-Taking in Corporate Entrepreneurs: An Experimental Pre-Test Design
- H-MoRe: Learning Human-centric Motion Representation for Action Analysis
- Computer-Assisted Creation of Employment Advertisements for the Development of Caregiver Community
- Prototype-Based Image Prompting for Weakly Supervised Histopathological Image Segmentation
- Multi-View Multi-Scale Network for 3D Object Recognition and Retrieval
- Homogeneous Dynamics Space for Heterogeneous Humans
- Immersive Ecological Virtual Environment for Inducing Balance Disturbances
- LinGen: Towards High-Resolution Minute-Length Text-to-Video Generation with Linear Computational Complexity
- Mimir: Improving Video Diffusion Models for Precise Text Understanding
- Enhancing Privacy-Utility Trade-offs to Mitigate Memorization in Diffusion Models
- Enhancing Healthcare Data Integrity and Access Control Using Blockchain and Industry 5.0
- Dynamic Power Tracking for Grid-Connected Microinverter PV Systems
- Active Elastic Scaling Strategy Based on Spatio-Temporal Graph Neural Network
- Seeing A 3D World in A Grain of Sand
- FlexGS: Train Once, Deploy Everywhere with Many-in-One Flexible 3D Gaussian Splatting
- Mind the Gaps: Toward a Unified Model of Multi-Cloud Firewall Configurations
- Q-PART: Quasi-Periodic Adaptive Regression with Test-time Training for Pediatric Left Ventricular Ejection Fraction Regression
- Triple Switch Flexible Step-Up Converter for Fuel Cell Electric Vehicle
- V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
- Discovering Hidden Visual Concepts Beyond Linguistic Input in Infant Learning
- Scenario Dreamer: Vectorized Latent Diffusion for Generating Driving Simulation Environments
- Adaptive Sketching Based Construction of H2 Matrices on GPUs
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction
- Doppelgangers++: Improved Visual Disambiguation with Geometric 3D Features
- Data-Based Adaptive Asymptotic Tracking Control for High-Speed Train: A Feedback Linearization Approach
- Protecting Your Video Content: Disrupting Automated Video-based LLM Annotations
- Impact of Mutual Flux on Rotor Position Estimation Using the Reluctance Equivalent Back-EMF Model for Synchronous Reluctance Motors
- AI in Public Procurement: Potential and Adoption in the Competitive Tendering Process
- Techno-Economic Comparison of State-of-Charge and State-of-Health Balancing in Second-Life Modular Battery Energy Storage Systems
- Unseen Visual Anomaly Generation
- ArtiFade: Learning to Generate High-quality Subject from Blemished Images
- Basket: A Large-Scale Video Dataset for Fine-Grained Skill Estimation
- Mamba for landslide detection: A lightweight model for mapping landslides with very high-resolution images
- Prediction of Alzheimer’s Disease Progression using Attention U-Net
- Energy-Efficient Aerial Base Station Enabled MBSFN: A Multi-Agent Reinforcement Learning Approach
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts
- SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting
- CUBO-to-QUBO Conversion: Reducing Cubic Formulations to Quadratic Formulations
- UniGraspTransformer: Simplified Policy Distillation for Scalable Dexterous Robotic Grasping
- DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation
- Unity in Diversity: Video Editing via Gradient-Latent Purification
- MV-SSM: Multi-View State Space Modeling for 3D Human Pose Estimation
- Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
- GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
- β-FFT: Nonlinear Interpolation and Differentiated Training Strategies for Semi-Supervised Medical Image Segmentation
- DiskVPS: Vanishing Point Detector via Hough Transform in a Disk Region
- AI-based Device for Fall Impact Reduction in Elder People
- Improving the accuracy of FEM simulations of time-domain inductive sensors through separation of secondary field effects
- All-Day Multi-Camera Multi-Target Tracking
- Dynamic voltage equalization approach for seriesconnected SiC MOSFETs Body Diodes
- A Novel Online Estimation Method for Low Equivalent Series Resisitance of Smoothing Capacitors
- Adaptive Parameter Selection for Tuning Vision-Language Models
- TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing
- Disentangled Pose and Appearance Guidance for Multi-Pose Generation
- A Reduced Switch Series Topology 15-level and 27level Multilevel Inverter
- Fault Detection for Train-Controlled On-Board Equipment Using a Hybrid CNN-LSTM Model
- LIM: Large Interpolator Model for Dynamic Reconstruction
- Enhancing Network Security with Intrusion Detection Systems in IoT Devices
- ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models
- MC 2 : Multi-concept Guidance for Customized Multi-concept Generation
- Enhancing Few-Shot Class-Incremental Learning via Training-Free Bi-Level Modality Calibration
- Joint Optimization of Secrecy Rate and Energy Consumption for RSMA in SAGIN via MADRL