- Over-the-Air Computation for Realizing Neural Link in In-network AI Architectures
- Research on Dunhuang Style Line Drawing Generation Based on Deep Learning
- AFL: A Single-Round Analytic Approach for Federated Learning with Pre-trained Models
- PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches
- A novel hybrid distribution transformer with integrated flexible voltage and current compensation capability
- Beyond Capabilities: How Indian R&D Subsidiaries Use Issue Selling to Shape Power and Innovation Mandates in a MNC
- CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset
- BERT-Based Joint Task Approach for Named Entity Recognition
- Lightning Current Distribution in an Electric Vehicle
- Structure from Collision
- Distraction is All You Need for Multimodal Large Language Model Jailbreaking
- Effect of Substrate Bias in Ohmic p-Gate GaN-HEMTs on Unclamped Inductive Switching Capability
- Cloud-Agnostic Serverless Platform for Fault-Tolerant Execution of Dynamic Task Graphs
- Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
- A Single-Stage Matrix Converter-based SRC-CV Controller for EV Charging Systems with an Integral Anti-Windup PI Controller
- PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing
- OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations
- EventFly: Event Camera Perception from Ground to the Sky
- AffordDP: Generalizable Diffusion Policy with Transferable Affordance
- Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
- A Review of Research on Privacy Breaches in Federated Learning
- FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation
- Fingerprinting Denoising Diffusion Probabilistic Models
- CroCoDL: Cross-device Collaborative Dataset for Localization
- FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
- Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation
- Concept Drift Mitigation on Resource-Constrained IoT Devices via Self-Learning
- vesselFM: A Foundation Model for Universal 3D Blood Vessel Segmentation
- Compositional Execution Motifs for Quantum-HPC Systems
- MobileMamba: Lightweight Multi-Receptive Visual Mamba Network
- Shaft Compliance as a Soft Sensor to Eliminate Stiction in Hybrid Haptic Devices
- Anomaly Detection in Video Surveillance using Deep Learning Techniques: A Review
- Explorative Evaluation of Validation Criteria for Validating Needs and Benefits of a Mobility Hub
- Dense Dispersed Structured Light for Hyperspectral 3D Imaging of Dynamic Scenes
- Lightweight Cloud-Based Phishing Email Detection using BERT and Deep Learning
- Design and Control of a Novel Position-Sensorless Wireless Permanent Magnet AC Motor
- Diffusion-based Event Generation for High-Quality Image Deblurring
- Deep Change Monitoring: A Hyperbolic Representative Learning Framework and a Dataset for Long-term Fine-grained Tree Change Detection
- Rethinking Lanes and Points in Complex Scenarios for Monocular 3D Lane Detection
- Facilitating Design for Additive Manufacturing with KG-based Retrieval-Augmented Generation
- Online Video Understanding: OVBench and VideoChat-Online
- Escaping Plato’s Cave: Towards the Alignment of 3D and Text Latent Spaces
- AnyMap: Learning a General Camera Model for Structure-from-Motion with Unknown Distortion in Dynamic Scenes
- MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Action Anticipation
- Bus Arrival Monitoring System using RFID Reader
- WeGen: A Unified Model for Interactive Multimodal Generation as We Chat
- Libra-Merging: Importance-Redundancy and Pruning-Merging Trade-Off for Acceleration Plug-In in Large Vision-Language Model
- SmartFruit: an Embedded AI System to Detect Fruit Ripeness and Prevent Food Waste
- Generative Hard Example Augmentation for Semantic Point Cloud Segmentation
- Efficient Detection of Relaxed Maximal Cliques in Large-Scale IoT Networks
- On the Application of Supervised Time Series Forest to Radio Frequency Fingerprinting
- 3D Prior is All You Need: Cross-Task Few-shot 2D Gaze Estimation
- Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
- ILIAS: Instance-Level Image retrieval At Scale
- Distilling Spectral Graph for Object-Context Aware Open-Vocabulary Semantic Segmentation
- ProAPO: Progressively Automatic Prompt Optimization for Visual Classification
- UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation
- Methodological Approach for Digital Transparency in the Lifecycle of Prefabricated Earth Composite Ceiling Systems in Industrial Construction – Integration of EPCIS 2.0 and ISO/IEC 8506
- Lift3D Policy: Lifting 2D Foundation Models for Robust 3D Robotic Manipulation
- Parallel Fractal Decomposition Optimization Algorithms on Heterogeneous Architectures
- Lifeline Connect: A Web-based Multi-Feature System for Mental Health Support
- Multi-feature Collaborative Attention Dynamic Hypergraph Convolutional Network for Hyperspectral Image Classification
- Comparative Analysis of PI and Fuzzy Logic Control in High-Efficiency Triple-Output DC-DC Converters
- HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis
- Enhancing Cluster Scheduling in HPC: A Continuous Transfer Learning for Real-Time Optimization
- CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Models
- DirectTriGS: Triplane-based Gaussian Splatting Field Representation for 3D Generation
- Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction
- FGI: Fast GNN Inference on Multi-Core Systems
- ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
- Smart Eye: A Surveillance system
- Speech Prediction in ANC Headphones for Improved Attenuation: New Methods and Perceptual Study
- AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTL
- Observation and Analysis of a Multiple Lightning Strike Based on Dynamic Vision
- Face Forgery Video Detection via Temporal Forgery Cue Unraveling
- Scattering Center Modeling Of Complex Targets Under Cross-polarization
- Rolling-Capacitors Topology: A Simplified Phase-modular Solution to Obtain Stepped-up Three-Phase Five-level AC from Single DC Source
- Obstacle Avoidance Distributed Tracking of Networked UAVs with Online Path Planning
- Watermarking One for All: A Robust Watermarking Scheme Against Partial Image Theft
- OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows
- 4D-Fly: Fast 4D Reconstruction from a Single Monocular Video
- Make them Socialites: Supporting Social Entrepreneurs
- Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression
- Adapting to Observation Length of Trajectory Prediction via Contrastive Learning
- 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
- Lightning-Terrain Association Mining Based on Improved Apriori Algorithm
- Research on the Construction and Operation Mode of Power Wireless Internet of Things Card Operation Management Platform
- ESCAPE: Equivariant Shape Completion via Anchor Point Encoding
- Compensation of a longitudinal excitation electromagnetic system for the detection of foreign bodies flowing in a pipe
- Knowledge-Aligned Counterfactual-Enhancement Diffusion Perception for Unsupervised Cross-Domain Visual Emotion Recognition
- ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
- PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generation
- Edit Away and My Face Will not Stay: Personal Biometric Defense against Malicious Generative Editing
- Free-viewpoint Human Animation with Pose-correlated Reference Selection
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering
- Powertrain Architecture and Control System Design for Overhead Line and Battery Powered Railway Tower Car
- 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