- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild
- Variance-Integrated Policy Optimization: A Maximum Entropy Approach for Localization in Energy Interconnection Systems
- Joint LDPC Code and Spreading Optimization for Multi-user Communications
- Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization
- A Novel Variable-Level ANPC Inverter with Capacitor Voltage Reconfiguration Method for 2 kV Photovoltaic Applications
- Enhancing Agricultural Decision Making with Machine Learning
- Reward Fine-Tuning Two-Step Diffusion Models via Learning Differentiable Latent-Space Surrogate Reward
- Double-Branched and Multi-Magnetic Directions Feature Fusion Network (DB&MDF2-Net) for the Accurate Reconstruction of Magnetic Particle Imaging
- Complex water surface image rain removal lightweight network based on convolution attention
- Alias-Free Latent Diffusion Models: Improving Fractional Shift Equivariance of Diffusion Latent Space
- Toward Greener AI-Based Smart Services: An Original Framework for Identifying Energy Efficiency Measurement Parameters
- AvianGuard-Signal Disruption Drone
- Integrated Sensing and Backscatter Communication with Movable Antennas: State-of-the-Art Survey and A Novel Inverse Scattering Framework
- Generalizable Object Keypoint Localization from Generative Priors
- HumanMM: Global Human Motion Recovery from Multi-shot Videos
- Exploring QUIC Dynamics: A Large-Scale Dataset for Encrypted Traffic Analysis
- Material Anything: Generating Materials for Any 3D Object via Diffusion
- Research on Adaptive Calibration Technique for Noncontact Voltage Sensors Based on Parameter-Independence Architecture
- Robust Remote Heart Rate Estimation Network Based on Spatial-Temporal-Channel Learning From Facial Videos
- Research on PCB Defect Detection Based on Yolo Algorithm
- Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy
- DEEP: Edge-Based Dataflow Processing with Hybrid Docker Hub and Regional Registries
- Video Depth without Video Models
- QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge
- Conformity Assessment of a Multi-Sensor Device for Indoor Environmental Quality Monitoring
- Tension Resolution in Sustainability Working Groups with Behavioral Mimicry
- A Bi-Level Multi-Objective System for Renewable Energy Self-Consumption: A Resident-Aware Approach to Leveraging Energy Flexibility
- Beyond Sight: Towards Cognitive Alignment in LVLM via Enriched Visual Knowledge
- MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
- Low-complexity look-up table-based frequency-domain trigonometric nonlinear equalizer for underwater wireless optical communications
- Masked Point-Entity Contrast for Open-Vocabulary 3D Scene Understanding
- Revisiting Audio-Visual Segmentation with Vision-Centric Transformer
- Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting
- Taming Teacher Forcing for Masked Autoregressive Video Generation
- CASP: Compression of Large Multimodal Models Based on Attention Sparsity
- Experimental Small-signal Characterization of Frequency Modulated Converters
- Air Quality Predictive Analysis using Empirical Mode Decomposition with Adaptive Noise-Bee Colony Optimization
- AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
- Improving Personalized Search with Regularized Low-Rank Parameter Updates
- Improved Activity Recognition Through Fusion of Earable Pairs
- Towards Understanding How Knowledge Evolves in Large Vision-Language Models
- A New Systematic Inverse Design Method of Pneumatic Soft Actuator for Precise Motion
- Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis
- Understanding Multi-Task Activities from Single-Task Videos
- Dual-Satellite Beam Illuminating Strategy for Load-Balanced LEO Beam Hopping Systems
- Vision Transformer based approach for accurately detecting cervical cancer
- Contrastive Learning-Based Agent Modeling for Deep Reinforcement Learning
- Design and Implementation of Static Wireless Power Transmission System in Electric Vehicles
- Optimal Transformer Turn Design of LLC Resonant Converters for High Efficient Operation
- LibraryX-ASIC: A First Look
- A Novel Formation Control Strategy for USVs With Improved DDPG: Simulation and Field Test
- TLPipe: An Efficient Two-Level Optimization Pipeline Model Parallelism for Large Model Training
- STDD: Spatio-Temporal Dual Diffusion for Video Generation
- EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision
- Towards Universal AI-Generated Image Detection by Variational Information Bottleneck Network
- Optimizing Traffic Anomaly Detection with Bertcapsule Model
- Investigation into the Reverse Recovery Dynamics of High-Voltage Fast Recovery Diodes
- RNG: Relightable Neural Gaussians
- Mind the Time: Temporally-Controlled Multi-Event Video Generation
- LoKi: Low-dimensional KAN for Efficient Fine-tuning Image Models
- CARL: A Framework for Equivariant Image Registration
- A 70–160-GHz Ultrawideband Amplifier Utilizing Reverse-Side Grounded Balun With Balance Compensation in 130-nm SiGe Process
- Unbalanced AC Grid Operation of a Power-Dense, Cost-Effective, and Efficient Hybrid Modular Multilevel Converter
- A Compressed QUBO Format for Traveling Salesperson Problems
- Predicting ocular diseases using squeezenet as feature maps with Convolutional Neural Networks
- Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing
- A Hybrid MobileNet-LSTM Model for Enhanced Detection of Deepfake Media in Real-Time Image and Video Analysis
- Constrained Stochastic Recursive Momentum Successive Convex Approximation
- Research on the Optimization of Heave Performance for Cylindrical FPSO Based on Surrogate Model
- Low-bitrate Light Field Video Compression Through Key Sequences Encoding and Joint Reconstruction Network
- Data-Driven Propulsion System Fault Diagnosis for Deep-Sea Submersible
- Thermally Stable High Power 1.3 μm InAs/GaAs Quantum Dot Distributed Feedback Laser Arrays
- A Lightweight Radio Frequency Fingerprint Recognition Method Based on Spatial Synergy Enhancing Attention
- Taillight Detection for Driving Intention Recognition in Multi-Scene Autonomous Driving
- SDFLMQ: A Semi-Decentralized Federated Learning Framework over MQTT
- Evaluation of Channel Mobility Extraction Methods Using Source-Separated Single Cell Structure for UMOSFET on 4H-SiC
- DualReward-QPE: Dual Reward-Based Query Preference Enhancement
- Collaborative Service Provisioning in IIoT Systems via Service Urgency and Situation-Adaptive Goal Modeling: A Dynamic Service–Energy Trade-off
- Efficient Privacy-Preserving Convolutional Neural Networks with CKKS-RNS for Encrypted Image Classification
- Less Attention is More: Prompt Transformer for Generalized Category Discovery
- Self-Commissioning Single-Inductor Dual-Output (SIDO) DC-DC Bi-Polar Converter
- SPARC: Score Prompting and Adaptive Fusion for Zero-Shot Multi-Label Recognition in Vision-Language Models
- LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
- Medical Image Object Detection via Layout-Aware Convolution and Optimal Transport Collaboration
- PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram
- Encoder-Aware Video Downscaling Using Encoding Parameters
- SACB-Net: Spatial-Awareness Convolutions for Medical Image Registration
- FSHNet: Fully Sparse Hybrid Network for 3D Object Detection
- HistoFS: Non-IID Histopathologic Whole Slide Image Classification via Federated Style Transfer with RoI-Preserving
- SfM-Free 3D Gaussian Splatting via Hierarchical Training
- Evaluating Expansion Memory for Optimizer State Offloading for Large Transformer Models
- MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
- MINIMA: Modality Invariant Image Matching
- SPR fiber optic biosensor based on AI-assisted design for immunoglobulin G biomarker detection
- NTR-Gaussian: Nighttime Dynamic Thermal Reconstruction with 4D Gaussian Splatting Based on Thermodynamics
- Pedestrian Trajectory Prediction Based on Multi-Relational Graph Convolution and Dynamic Attention
- Towards Automated or Assisted Requirements Extraction and Analysis Using an LLM-Based Multi-Agent System: A Case Study
- HyperGS: Hyperspectral 3D Gaussian Splatting
- PLeaS — Merging Models with Permutations and Least Squares
- Two by Two: Learning Multi-Task Pairwise Objects Assembly for Generalizable Robot Manipulation