- MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
- 3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
- STEPS: Sequential Probability Tensor Estimation for Text-to-Image Hard Prompt Search
- Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation
- A New Method for Temperature Measurement of Wire Rod Based on Adaptive Exposure Time
- A Planar Transformer Winding Configuration for High Frequency DAB Converter with Common-Mode EMI Mitigation
- SLDB: An End-To-End Heterogeneous System-on-Chip Benchmark Suite for LLM-Aided Design
- Research on the Security of Time-Sensitive Networking Enabled Industrial Control System
- Co-op: Correspondence-based Novel Object Pose Estimation
- Eval3D: Interpretable and Fine-Grained Evaluation for 3D Generation
- Lightweight Neural Network With Fixed Classifier for Enhanced Drone RF Signal Recognition
- 3D Student Splatting and Scooping
- DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
- Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMs
- Taxonomy-Aware Evaluation of Vision–Language Models
- Novel Coil Pitch Configuration of Rectangular coil for Improved Misalignment Tolerance in Wireless Charging of EVs
- Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank Adaptation
- BootPlace: Bootstrapped Object Placement with Detection Transformers
- A Simulation-Based Framework to Reduce I/O Contention in HPC
- INSPIRIT: Adaptive Priority-based Task Scheduling for Heterogeneous Hardware
- MatAnyone: Stable Video Matting with Consistent Memory Propagation
- 3D-HGS: 3D Half-Gaussian Splatting *
- LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation
- High-Performance Surface Plasmon Resonance Sensor for Pathogenic Cancer Detection Using Ag/Si/EuS Layers
- Mamba-Adaptor: State Space Model Adaptor for Visual Recognition
- DiMAT Materials Modeler (DiMM): An Interactive Framework for Materials Property Prediction and Optimization Using a Hybrid Machine Learning - Genetic Algorithm Approach
- AniGS: Animatable Gaussian Avatar from a Single Image with Inconsistent Gaussian Reconstruction
- Comprehensive Information Bottleneck for Unveiling Universal Attribution to Interpret Vision Transformers
- Weakly Supervised Semantic Segmentation via Progressive Confidence Region Expansion
- Bilateral Tensor Ring Decomposition for Thick Cloud Removal in Multitemporal Remote Sensing Images
- Multimedia Information Management and Control of University Laboratory Based on Intelligent Scene in Data Edge Computing
- End-to-End Implicit Neural Representations for Classification
- Dual-Agent Optimization framework for Cross-Domain Few-Shot Segmentation
- On-Device Crack Segmentation for Edge Structural Health Monitoring
- Driver Fatigue Detection Based on BiLSTM-At and Multi-Source Information Fusion
- Mesh Mamba: A Unified State Space Model for Saliency Prediction in Non-Textured and Textured Meshes
- Gazing at Rewards: Eye Movements as a Lens into Human and AI Decision-Making in Hybrid Visual Foraging
- VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step
- OFER: Occluded Face Expression Reconstruction
- Real Time Feedforward Decoupled Control of Triple Active Bridge Converter for Charging of Electric Vehicles
- A Novel Start-up Methodology for GaN HEMT-Based Ripple Power Compensation Integrated Totem-Pole PFC Converters
- ProHOC: Probabilistic Hierarchical Out-of-Distribution Classification via Multi-Depth Networks
- Steepest Descent Density Control for Compact 3D Gaussian Splatting
- UPME: An Unsupervised Peer Review Framework for Multimodal Large Language Model Evaluation
- An Intelligent IoT Navigation System for Visually Impaired Individuals: Design and Implementation
- Advancing Cloud-Edge Applications Through Fog-Cloud Integration and Low-Latency Edge Solutions: A Narrative Case Study From Veterans Engineering
- Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models
- PosterMaker: Towards High-Quality Product Poster Generation with Accurate Text Rendering
- Learning Visual Composition through Improved Semantic Guidance
- Transformers without Normalization
- FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training
- Agentic AI for Microservices: Autonomous Optimization of High-Volume Financial Transactions in Cloud Native Environments
- LesionLocator: Zero-Shot Universal Tumor Segmentation and Tracking in 3D Whole-Body Imaging
- Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
- NADER: Neural Architecture Design via Multi-Agent Collaboration
- CleanDIFT: Diffusion Features without Noise
- Generative Modeling of Class Probability for Multi-Modal Representation Learning
- Fractal Calibration for long-tailed object detection
- Design and Deployment of a Remaining Useful Life Estimation Algorithm of Power Switches in a Cloud Computing Environment
- Omni-ID: Holistic Identity Representation Designed for Generative Tasks
- Dual Focus-Attention Transformer for Robust Point Cloud Registration
- Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models
- Learning on Model Weights using Tree Experts
- Enhanced then Progressive Fusion with View Graph for Multi-View Clustering
- Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
- Probability Density Geodesics in Image Diffusion Latent Space
- Self-Supervised Large Scale Point Cloud Completion for Archaeological Site Restoration
- UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
- Enabling Manual-Controllable Compilation for Dataflow CGRAs
- A Distractor-Aware Memory for Visual Object Tracking with SAM2
- On the Influence of the SNR on the Optimization of Two-Satellite Systems with AOA Receivers
- MambaIRv2: Attentive State Space Restoration
- Lifting Motion to the 3D World via 2D Diffusion
- Similarity-Guided Layer-Adaptive Vision Transformer for UAV Tracking
- A capacity configuration strategy for marine hybrid power storage system
- Black Hole-Driven Identity Absorbing in Diffusion Models
- Numerical Simulation Analysis of the Direct Effects of Lightning on Electric Vehicles
- 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer
- Low Resource Passive Acoustic Vessel Detectors: Performance and System Design for Challenging Acoustic Environments
- PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
- Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation
- Novel Single-Stage Integrated Active Filter Isolated Matrix-Type Three-Phase AC/DC Converter (IAF-iMR)
- A Bias-Free Training Paradigm for More General AI-generated Image Detection
- Development of a Remote Monitoring System for Intelligent All-Electric Ships Based on 4G Network and Web Technology
- Robotic Visual Instruction
- Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Dataset
- UniScene: Unified Occupancy-centric Driving Scene Generation
- MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures
- Unbiasing through Textual Descriptions: Mitigating Representation Bias in Video Benchmarks
- Research on MPPT of Photovoltaic Based on IWOA
- DT-Assisted Vehicular Crowdsensing Through Semantic-Aware NDN
- GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving
- RAEncoder: A Label-Free Reversible Adversarial Examples Encoder for Dataset Intellectual Property Protection
- Research and Development of Rotating Structure Analysis Module Based on SiPESC.FEMS
- Conical Visual Concentration for Efficient Large Vision-Language Models
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image
- Cloud-Accelerated Personalized Cancer Treatment Prediction Using Adaptive Quantum-Inspired Evolutionary Algorithm and Graph Neural Networks
- VolFormer: Explore More Comprehensive Cube Interaction for Hyperspectral Image Restoration and Beyond
- Multi-Switch Fault Analysis of Six-Phase Inverters Using CNN and Data Augmentation with Limited Training Dataset Utilization
- NAIA: A Multi-Technology Virtual Assistant for Boosting Academic Environments – A Case Study