- Hierarchical Flow Diffusion for Efficient Frame Interpolation
- SEAL: SEmantic Attention Learning for Long Video Representation
- A Dynamic Approach to Load Balancing in Cloud Infrastructure: Enhancing Energy Efficiency and Resource Utilization
- Active Diffusion Matching: Score-Based Iterative Alignment of Cross-Modal Retinal Images
- Enhanced Cascaded Object Detection Network Based on Indirect Self-Attention Mechanism
- Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification
- SeedVR: Seeding Infinity in Diffusion Transformer Towards Generic Video Restoration
- Imperfect Recognition: A Study of OCR Limitations in the Context of Scientific Documents
- Impact of Stem Branches Evolution on the Subsequent Development of Positive Leaders
- Two-Level Phase-shift Circulant Modulation for Bidirectional Isolated Modular DC-DC Converter With Natural-Balance Capability
- DrVideo: Document Retrieval Based Long Video Understanding
- Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos
- A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
- FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentation
- Exploiting Temporal State Space Sharing for Video Semantic Segmentation
- HyperFree: A Channel-adaptive and Tuning-free Foundation Model for Hyperspectral Remote Sensing Imagery
- Impact assessment of optimally integrated green energy resources on microgrid loss allocation using an efficient distribution power flow algorithm
- GROVE: A Generalized Reward for Learning Open-Vocabulary Physical Skill
- Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
- Efficient Video Face Enhancement with Enhanced Spatial-Temporal Consistency
- From Head to Tail: Efficient Black-box Model Inversion Attack via Long-tailed Learning
- R-TPT: Improving Adversarial Robustness of Vision-Language Models through Test-Time Prompt Tuning
- A Real-Time Monitoring System for User Attentivity on e-learning platforms
- Predicting Important Photons for Energy-Efficient Single-Photon Videography
- Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis
- Beyond Generation: A Diffusion-based Low-level Feature Extractor for Detecting AI-generated Images
- Synergizing Motion and Appearance: Multi-Scale Compensatory Codebooks for Talking Head Video Generation
- A T A: Adaptive Transformation Agent for Text-Guided Subject-Position Variable Background Inpainting
- Deep Reinforcement Learning-Based Adaptive Bandpass Filter With Reconfigurable Frequency and Bandwidth
- Multi-Label Black-Box Attacks via Evolutionary Structured Many-Objective Adversarial Perturbations
- Single-Stage Solar PV Wireless Charging System for Electric Vehicles Ultra-Wide Voltage Applications
- BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
- TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
- LMO: Linear Mamba Operator for MRI Reconstruction
- Automation in Inventory Redistribution within a Hybrid Supply Chain with Reverse Logistics: A Heuristic Approach Based on Business Rules
- Gaussian Splatting Feature Fields for (Privacy-Preserving) Visual Localization
- Multi-Light Bidirectional Path Tracing Based on Triangle Grids
- EPSRQ: Efficient Privacy-preserving Spatial-keyword Range Query Processing in Cloud
- Adaptive Policy-Driven Network Intelligence for Edge-to-Cloud Continuum
- Research on Dynamic Navigation and Obstacle Avoidance of Mobile Robots in Open Office
- EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space Duality
- RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins
- ARTEMIS: Adaptive Real-Time Task Execution & Management in Heterogeneous Systems
- Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
- Towards Event-Driven Aerodynamic Monitoring of Wind Turbine Blades Using PVDF and MEMS Sensors
- PV based Sensors for Smart Street Light Fault Detection and Tracking
- LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty
- A Generalized Analytical Gain Model for CLLC Resonant Converter with Asymmetric Parameters
- Massive MIMO Beam ID-Based Positioning Method With Low Earth Orbit Satellite Mega Constellations
- Novel Synthesis Method for Wideband BPF With Additional Insertion Phase Shift and True Time Delay
- GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation
- Textured Gaussians for Enhanced 3D Scene Appearance Modeling
- Exploration of LLM Lossless Compression on Scientific Data
- Coupled Electromagnetic and Heat Analysis of a ZnO Disk with the FDTD Method in the 2D Cylindrical Coordinate System
- IM-Portrait: Learning 3D-aware Video Diffusion for Photorealistic Talking Heads from Monocular Videos
- Observations of Rocket Triggered Lightning Discharge in Winter Thunderstorms in Japan Using a Broadband VHF Interferometer
- Multi-Scale Perceptual Learning for Skin Lesion Image Segmentation
- Study of Current Control for High-Speed Motor Drive Systems
- Diabetes Prediction Model Based on SVM Optimized with RF Feature Selection and GWO
- Research on Automatic Extraction of Key Parameters of Lightning Risk Assessment Based on Laser Point Cloud of Transmission Line
- DATAWiSE: A Scalable Big Data Reference Architecture for Smart Building
- VideoDirector: Precise Video Editing via Text-to-Video Models
- Ref-GS: Directional Factorization for 2D Gaussian Splatting
- SAIST: Segment Any Infrared Small Target Model Guided by Contrastive Language-Image Pretraining
- All-directional Disparity Estimation for Real-world QPD Images
- Reconstructing Humans with a Biomechanically Accurate Skeleton
- Study on the Characteristics of Intense Lightning Activity During a Spring Severe Thunderstorm Process in Southern China
- Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
- CustAny: Customizing Anything from A Single Example
- Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
- Improving LLM-Powered EDA Assistants with RAFT
- Argus: A Compact and Versatile Foundation Model for Vision
- A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
- M3amba: Memory Mamba is All You Need for Whole Slide Image Classification
- Characterizing the Influence of Circuit Parasitics and Operating Conditions on a Passive Regenerative Snubber for Phase-Shifted Full-Bridge Converter
- Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
- SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception
- Green Edge Computing Based IoV Dynamic Task Collaborative Strategy
- Vehicle Routing Incorporating Implicit Preferences: An Omnidimensional Human–Algorithm Collaboration Approach
- Any6D: Model-free 6D Pose Estimation of Novel Objects
- Cheb-GR: Rethinking k-nearest neighbor search in Re-ranking for Person Re-identification
- DDIP: Mutual-Regularized Dual Deep Image Prior for Self-Supervised Compressive Spectral Imaging
- AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
- Hardware-Rasterized Ray-Based Gaussian Splatting
- Control of Integrated Magnetic-Based Active Harmonic Filter for Three-Phase Standalone Application
- Development and Deployment of a Genomic Cancer Data Extraction Pipeline on the Cloud
- OSV: One Step is Enough for High-Quality Image to Video Generation
- COSMIC: Clique-Oriented Semantic Multi-space Integration for Robust CLIP Test-Time Adaptation
- Directional Label Diffusion Model for Learning from Noisy Labels
- AdMiT: Adaptive Multi-Source Tuning in Dynamic Environments
- Design2GarmentCode: Turning Design Concepts to Tangible Garments Through Program Synthesis
- Fine-Grained Skin Wound Segmentation Based on Machine Learning with Scribble Annotations
- Combined Model for P-S or S-P Configured Lithium-ion Batteries and Equalization Electronics for Spacecraft
- RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
- ImViD: Immersive Volumetric Videos for Enhanced VR Engagement
- Reanimating Images using Neural Representations of Dynamic Stimuli
- Gen-AI in a Bottle: Experiments with LLMs to Generate HPC Kernels
- Assembly of FETI dual operator using CUDA
- SketchFusion: Learning Universal Sketch Features through Fusing Foundation Models
- GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis *