Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 42,121 to 42,130 of 223,853 articles

AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation

arXiv Mar 13, 2026
Diffusion Transformers (DiTs) are a dominant backbone for high-fidelity text-to-image generation due to strong scalability and alignment at high resolutions. However, quadratic self-attention over dense spatial tokens leads to high inference latency ... read more 
Computer Vision and Pattern Recognition

DINOLight: Robust Ambient Light Normalization with Self-supervised Visual Prior Integration

arXiv Mar 13, 2026
This paper presents a new ambient light normalization framework, DINOLight, that integrates the self-supervised model DINOv2's image understanding capability into the restoration process as a visual prior. Ambient light normalization aims to restore ... read more 
Computer Vision and Pattern Recognition

Multiscale Structure-Guided Latent Diffusion for Multimodal MRI Translation

arXiv Mar 13, 2026
Although diffusion models have achieved remarkable progress in multi-modal magnetic resonance imaging (MRI) translation tasks, existing methods still tend to suffer from anatomical inconsistencies or degraded texture details when handling arbitrary m... read more 
Image and Video Processing cs.AI cs.CV

MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement

arXiv Mar 13, 2026
Cross-view geo-localization (CVGL) aims to accurately localize street-view images through retrieval of corresponding geo-tagged satellite images. While prior works have achieved nearly perfect performance on certain standard datasets, their robustnes... read more 
Computer Vision and Pattern Recognition

SDF-Net: Structure-Aware Disentangled Feature Learning for Opticall-SAR Ship Re-identification

arXiv Mar 13, 2026
Cross-modal ship re-identification (ReID) between optical and synthetic aperture radar (SAR) imagery is fundamentally challenged by the severe radiometric discrepancy between passive optical imaging and coherent active radar sensing. While existing a... read more 
Computer Vision and Pattern Recognition

Feynman: Knowledge-Infused Diagramming Agent for Scalable Visual Designs

arXiv Mar 13, 2026
Visual design is an essential application of state-of-the-art multi-modal AI systems. Improving these systems requires high-quality vision-language data at scale. Despite the abundance of internet image and text data, knowledge-rich and well-aligned ... read more 
Machine Learning cs.AI cs.HC cs.MA cs.SE

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating

arXiv Mar 13, 2026
Large Vision-Language Models (LVLMs) have shown remarkable potential across a wide array of vision-language tasks, leading to their adoption in critical domains such as finance and healthcare. However, their growing deployment also introduces signifi... read more 
Computer Vision and Pattern Recognition

Prompt-Driven Lightweight Foundation Model for Instance Segmentation-Based Fault Detection in Freight Trains

arXiv Mar 13, 2026
Accurate visual fault detection in freight trains remains a critical challenge for intelligent transportation system maintenance, due to complex operational environments, structurally repetitive components, and frequent occlusions or contaminations i... read more 
Computer Vision and Pattern Recognition eess.IV

VLM4Rec: Multimodal Semantic Representation for Recommendation with Large Vision-Language Models

arXiv Mar 13, 2026
Multimodal recommendation is commonly framed as a feature fusion problem, where textual and visual signals are combined to better model user preference. However, the effectiveness of multimodal recommendation may depend not only on how modalities are... read more 
Information Retrieval cs.AI cs.CV

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

arXiv Mar 13, 2026
Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against a single c... read more 
Computer Vision and Pattern Recognition
Popular Topics
Recent Journals