- Adversarial Robust Salient Object Detection in Optical Remote Sensing Images with Implicit Feature Enhancement
- Battery Capacity Prediction Method Based on Jamba Model
- Scheduling Strategies for Partially-Replicable Task Chains on Two Types of Resources
- Efficient Continual Learning in Keyword Spotting using Binary Neural Networks
- Twinner: Shining Light on Digital Twins in a Few Snaps
- Hybrid Concept Bottleneck Models
- Skip Tuning: Pre-trained Vision-Language Models are Effective and Efficient Adapters Themselves
- Crab: A Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
- Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
- Digital Products Based on Large Language Models for the Exploration of Graph-Databases in Materials Science and Manufacturing
- Design of Multi-UAV Task Allocation Algorithm Based on Deep Reinforcement Learning
- Multilevel FFT Method for Surface-to-Volume Field Propagation in Electrically-Large Dielectric Objects
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction
- AlignMamba: Enhancing Multimodal Mamba with Local and Global Cross-Modal Alignment
- Overview of Research on Low-Resource Language Machine Translation Based on Artificial Intelligence
- Single-Phase Bridge Inverter with Modified LCLLC Filter
- GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors
- Multi-modal Medical Diagnosis via Large-small Model Collaboration
- TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond
- Calibrated Uncertainty Estimation for Trustworthy Deep IoT Attack Detection
- GeoDepth: From Point-to-Depth to Plane-to-Depth Modeling for Self-Supervised Monocular Depth Estimation
- BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
- Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise
- UniSTD: Towards Unified Spatio-Temporal Learning across Diverse Disciplines
- WISE: A Framework for Gigapixel Whole-Slide-Image Lossless Compression
- DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
- Improved monocular depth prediction using distance transform over pre-semantic contours with self-supervised neural networks
- Adaptive Model based Stator Interturn Fault Detection in Sensorless PMSM Drive
- Stable Task Allocation in Mobile Crowdsensing: An Interruption-Driven Approach
- CDI: Copyrighted Data Identification in Diffusion Models
- Exploring Timeline Control for Facial Motion Generation
- Training-free Dense-Aligned Diffusion Guidance for Modular Conditional Image Synthesis
- Buck-Converter-Based Inductor Loss Emulator for Multiple Power Electronics Applications
- Parametric Point Cloud Completion for Polygonal Surface Reconstruction
- Multifrequency Model of Sinusoidal PWM by DIDR Methodology
- LLM-driven Multimodal and Multi-Identity Listening Head Generation
- Research on Life Prediction of Surge Protective Device Based on Machine Learning
- Task Singular Vectors: Reducing Task Interference in Model Merging
- Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think
- Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision
- WeatherGen: A Unified Diverse Weather Generator for LiDAR Point Clouds via Spider Mamba Diffusion
- Blind Bitstream-corrupted Video Recovery via Metadata-guided Diffusion Model
- Certified Human Trajectory Prediction
- GLane3D : Detecting Lanes with Graph of 3D Keypoints
- Towards QoS-Aware Serverless Function Offloading in the Edge-Cloud Continuum through Reinforcement Learning
- Minimizing Sensory Habituation in Nerve Stimulation Through Strategic Temporal Stimulation Patterns
- Test-time Forward Model Adaptation for Seismic Deconvolution
- EditAR: Unified Conditional Generation with Autoregressive Models
- Open-World Amodal Appearance Completion
- Prompt2Perturb (P2P): Text-Guided Diffusion-Based Adversarial Attacks on Breast Ultrasound Images
- Layer-and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
- Research on Dunhuang Style Line Drawing Generation Based on Deep Learning
- VideoSPatS: Video SPatiotemporal Splines for Disentangled Occlusion, Appearance and Motion Modeling and Editing
- Modeling and Optimization of Partial Disassembly Line Balancing Problem Considering Interactions Among Precedence Free Tasks
- The Holonomy of Optimal Mass Transport: The Gaussian-Linear Case
- BERT-Based Joint Task Approach for Named Entity Recognition
- FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute
- Integrating AI Chatbots in Customer Service for Credit Card Companies
- Manufacturing and Reliability of Low Parasitic Capacitance Flip Chip SiC Power Module
- Lightning-Terrain Association Mining Based on Improved Apriori Algorithm
- GENIUS: A Generative Framework for Universal Multimodal Search
- Effect of Substrate Bias in Ohmic p-Gate GaN-HEMTs on Unclamped Inductive Switching Capability
- A Decoupled Coarse-Grained Reconfigurable Architecture by Introducing Data Flow Management Unit
- Optimizing Cartographer for Indoor Mapping and Analysis
- Research on Underwater Image Enhancement Technology Based on Physical Modeling and Deep Learning
- OpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design
- Minimizing Labeled, Maximizing Unlabeled: An Image-Driven Approach for Video Instance Segmentation
- Compensation of a longitudinal excitation electromagnetic system for the detection of foreign bodies flowing in a pipe
- TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion
- Dense Dispersed Structured Light for Hyperspectral 3D Imaging of Dynamic Scenes
- Opportunistic Single-Photon Time of Flight
- Interpretable Generative Models through Post-Hoc Concept Bottlenecks
- Lightweight Cloud-Based Phishing Email Detection using BERT and Deep Learning
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering
- Harnessing 3D-CNN, GRU, and Attention Mechanisms for Next-Generation Crop Yield Forecasting
- SecDV: A Lightweight Secure Deep Neural Network Inference Service with Dynamic Verification
- Radar compound deception jamming recognition based on fast-slow time-frequency distributions
- Development of a BIM-Data Mining Integrated Digital Twin and Its Use for Lifecycle Management Tools
- MenTeR: A fully-automated Multi-agenT workflow for end-to-end RF/Analog Circuits Netlist Design
- WISNet: Pseudo Label Generation on Unbalanced and Patch Annotated Waste Images
- Open-World Objectness Modeling Unifies Novel Object Detection
- Lightweight Generative AI on Edge Devices: Pruning Strategies for VGG-16 and MobileNet on CIFAR
- GBlobs: Explicit Local Structure via Gaussian Blobs for Improved Cross-Domain LiDAR-based 3D Object Detection
- Label Shift Meets Online Learning: Ensuring Consistent Adaptation with Universal Dynamic Regret
- Instruction-based Image Manipulation by Watching How Things Move
- OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
- Mode-transition Analysis for Safe-operation of Reconfigurable On-Board Converter for Electric Vehicles
- A Machine Anomalous Sound Detection Method Based on Deep Residual Generative Adversarial Network
- Machine Learning-based Trajectory Planning for Single-loop Flatness-based Control of PMSMs
- Navigating the Unseen: Zero-shot Scene Graph Generation via Capsule-Based Equivariant Features
- Octopus: Alleviating Hallucination via Dynamic Contrastive Decoding
- Zero-1-to-A: Zero-Shot One Image to Animatable Head Avatars Using Video Diffusion
- Design and Implementation of a Cloud-Based Water Environment Monitoring System Using Internet of Things
- Robust Methodology Design to Predict Opioid Overdose System based on AI Assisted Deep Learning Principles
- TinyEEGConformer: An Attention-Based EEG Decoding Model for Embedded Systems
- RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness
- Effective SAM Combination for Open-Vocabulary Semantic Segmentation
- SpiralShard: Highly Concurrent and Secure Blockchain Sharding via Linked Cross-Shard Endorsement
- HPPC-Based ECM Parameter Optimisation of Lithium-ion Battery: A Comparative Analysis of Non-Linear Least Squares Methods
- One Model for ALL: Low-Level Task Interaction Is a Key to Task-Agnostic Image Fusion