- Dynamic Integration of Task-Specific Adapters for Class Incremental Learning
- Lossy Parallel Visualization of Large-Scale Volume Data with Error-Bounded Image Compositing
- Non-Iterative Coordination of Interconnected Power Grids via Dimension-Decomposition-Based Flexibility Aggregation
- AdaCM 2 : On Understanding Extremely Long-Term Video with Adaptive Cross-Modality Memory Reduction
- Comprehensive Analysis and Wide Range Operation of ZVS and Quasi-ZPA in Wireless Power Transfer System
- Joint Out-of-Distribution Filtering and Data Discovery Active Learning
- Ground-V: Teaching VLMs to Ground Complex Instructions in Pixels
- MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans
- Video Motion Transfer with Diffusion Transformers
- Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
- Benchmarking Sustainability Assessment Tools for SMEs: An AHP–TOPSIS Framework and a Vision–Execution Quadrant Approach
- Educational Institution Financial Management System Based on Enhanced Smart Contracts
- Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior
- LoRA Subtraction for Drift-Resistant Space in Exemplar-Free Continual Learning
- Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
- AI-Driven Optimization of Wave-Controlled Reconfigurable Intelligent Surfaces
- Convex Combination Star Shape Prior for Data-driven Image Semantic Segmentation
- GazeGene: Large-scale Synthetic Gaze Dataset with 3D Eyeball Annotations
- Free Lunch Enhancements for Multi-modal Crowd Counting
- ResCLIP: Residual Attention for Training-free Dense Vision-language Inference
- DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation
- BEVDiffuser: Plug-and-Play Diffusion Model for BEV Denoising with Ground-Truth Guidance
- Iterative Sound Source Recognition Method Based on Randomness Removal
- Research on Sentiment Analysis Method Based on the Collaborative Modeling of Attention Mechanism and Sentiment Lexicon
- A System Identification Approach to Modelling Chlorophyll Fluorescence Response to Dynamic Light Conditions
- Exo-Glove Pinch: A Soft, Hand-Wearable Robot Designed Through Constrained Tendon Routing Analysis
- Single Event Transient Characterization of a Low-Dropout Regulator in a sub-20 nm CMOS Technology
- Generative Zero-Shot Composed Image Retrieval
- IRISX: A Dynamic Trade-off System for Harnessing Heterogeneity for Performance Portability
- Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
- Design and Performance Analysis of Planar Antenna for Ground Penetrating Radar Applications
- InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
- Accelerating Multimodal Large Language Models by Searching Optimal Vision Token Reduction
- Generalized Gaussian Entropy Model for Point Cloud Attribute Compression with Dynamic Likelihood Intervals
- Joint Optimization of Underwater Acoustic ISUDC Waveform Design and Sparse Channel Estimation Algorithms
- DiSciPLE: Learning Interpretable Programs for Scientific Visual Discovery
- Enhancing Time-Domain Shielding Effectiveness of Cables Using Metal-Coated Aramid-Fiber Composites
- Shadow Generation Using Diffusion Model with Geometry Prior
- Where’s the liability in the Generative Era? Recovery-based Black-Box Detection of AI-Generated Content
- Research on Dual Objectives Optimization of Quality and Cost Based on MCMC-ACO and Dynamic Bayesian Integration in Multi-Process Electronics Manufacturing
- MotionPro: A Precise Motion Controller for Image-to-Video Generation*
- Research on Trajectory Tracking Control Algorithm for Medical Delivery Robot
- AMSnet 2.0: A Large AMS Database with AI Segmentation for Net Detection
- Analysis of higher-order Lotka-Volterra models: Application of S-tensors and the polynomial complementarity problem
- Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
- Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion
- VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding
- Spectral State Space Model for Rotation-Invariant Visual Representation Learning
- Generative Photomontage
- Research and Implementation of an Automatic Secondary Security Verification Method for System Operation Permissions
- Design and simulation analysis of ship automatic anti-interference heading controller
- Compositional Caching for Training-free Open-vocabulary Attribute Detection
- VidSeg: Training-free Video Semantic Segmentation based on Diffusion Models
- VIRES: Video Instance Repainting via Sketch and Text Guided Generation
- PICD: Versatile Perceptual Image Compression with Diffusion Rendering
- ALIEN: Implicit Neural Representations for Human Motion Prediction under Arbitrary Latency
- COAP: Memory-Efficient Training with Correlation-Aware Gradient Projection
- Zero-Shot Monocular Scene Flow Estimation in the Wild
- Unveiling collective value creation behavior in public projects: The stakeholder value network approach
- Multitwine: Multi-Object Compositing with Text and Layout Control
- Modeling Thousands of Human Annotators for Generalizable Text-to-Image Person Re-identification
- OmniGen: Unified Image Generation
- From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
- A Regularization-Guided Equivariant Approach for Image Restoration
- YOLO-Poppy: Opium Poppy Detection Algorithm for Complex Aerial Scenes
- SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal
- Performance Modeling of Non-Uniform Heterogeneous Platforms
- Embedding Generative AI into Products – 10 Design Principles for Building Intelligent Systems
- An Example of Autism Co-Design: Physiological Sensor-driven Ecological Momentary Assessment Application
- Investigating CNN Models Efficacy in Spotting Lung Conditions using X-Ray Images
- Show and Segment: Universal Medical Image Segmentation via In-Context Learning
- MambaVision: A Hybrid Mamba-Transformer Vision Backbone
- MATCHA: Towards Matching Anything
- Optimus-2 : Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy
- Construction of Automated Machine Learning (AutoML) Framework Based on Large Language Models
- Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
- Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space
- MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
- CRT-AS: A Chinese Remainder Theorem-Based Authentication and Key Agreement Scheme for SDVN
- VGGT: Visual Geometry Grounded Transformer
- POMP: Physics-constrainable Motion Generative Model through Phase Manifolds
- Implementation of Cryptographic Architecture for Secure Data Transmission using Reversible Logic Gates
- Template-Adaptive Content Organization: AI-Driven Personalization for E-Commerce Email Marketing
- A Novel Three Port Multi-Input Single Inductor DC-DC Bidirectional Boost Converter
- Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal
- Comprehensive Comparative Study On Peak Particle Velocity Prediction For Surface Mines Via A Machine Learning Approach
- Bayesian Test-Time Adaptation for Vision-Language Models
- Assessing the Impact of Industrial Energy Reductions on Electric Truck Adoption
- Model-Based Failure Propagation Analysis and Automated Fault Tree Generation: Methodology and Application in Complex Avionics System
- A Modulation Scheme for Enhanced Performance of Hybrid Source Inverters in Electric Vehicles Application
- Highly Integrated Communication System for Commercial SAR Satellites Based on On-Board Computers
- CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction
- Simple Derivation of Approximate Crosstalk Expressions for Multicore Fibers With Core-Dependent Loss
- Ultra-Efficient Three-Phase Integrated-Active-Filter Isolated Rectifier for AI Data Center Applications
- Mechanical Parameters Identification of Servo Drive Using Periodic Velocity Profile
- Research on the Design of a Multi-User Interactive System for Chu Music Based on Multimodal Collaboration
- SUM Parts: Benchmarking Part-Level Semantic Segmentation of Urban Meshes
- One-for-More: Continual Diffusion Model for Anomaly Detection
- Learning Visual Generative Priors without Text
- DPU: Dynamic Prototype Updating for Multimodal Out-of-Distribution Detection