Artificial Intelligence Medical Compendium

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

Showing 31,501 to 31,510 of 220,544 articles

PrivEraserVerify: Efficient, Private, and Verifiable Federated Unlearning

arXiv Apr 14, 2026
Federated learning (FL) enables collaborative model training without sharing raw data, offering a promising path toward privacy preserving artificial intelligence. However, FL models may still memorize sensitive information from participants, conflic... read more 
Machine Learning

Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration

arXiv Apr 14, 2026
Automated diagnosis based on color fundus photography is essential for large-scale glaucoma screening. However, existing deep learning models are typically data-driven and lack explicit integration of retinal anatomical knowledge, which limits their ... read more 
Computer Vision and Pattern Recognition

Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection

arXiv Apr 14, 2026
In recent years, the rapid development of generative artificial intelligence technology has significantly lowered the barrier to creating high-quality fake images, posing a serious challenge to information authenticity and credibility. Existing gener... read more 
Computer Vision and Pattern Recognition

OmniFood8K: Single-Image Nutrition Estimation via Hierarchical Frequency-Aligned Fusion

arXiv Apr 14, 2026
Accurate estimation of food nutrition plays a vital role in promoting healthy dietary habits and personalized diet management. Most existing food datasets primarily focus on Western cuisines and lack sufficient coverage of Chinese dishes, which restr... read more 
Computer Vision and Pattern Recognition

ReflectCAP: Detailed Image Captioning with Reflective Memory

arXiv Apr 14, 2026
Detailed image captioning demands both factual grounding and fine-grained coverage, yet existing methods have struggled to achieve them simultaneously. We address this tension with Reflective Note-Guided Captioning (ReflectCAP), where a multi-agent p... read more 
Artificial Intelligence cs.CV

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

arXiv Apr 14, 2026
We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents, from brow... read more 
Computer Vision and Pattern Recognition

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

arXiv Apr 14, 2026
We study typographic prompt injection attacks on vision-language models (VLMs), where adversarial text is rendered as images to bypass safety mechanisms, posing a growing threat as VLMs serve as the perceptual backbone of autonomous agents, from brow... read more 
Computer Vision and Pattern Recognition

Dual-Modality Anchor-Guided Filtering for Test-time Prompt Tuning

arXiv Apr 14, 2026
Test-Time Prompt Tuning (TPT) adapts vision-language models using augmented views, but its effectiveness is hindered by the challenge of determining which views are beneficial. Standard entropy-based filtering relies on the internal confidence scores... read more 
Computer Vision and Pattern Recognition

DeferredSeg: A Multi-Expert Deferral Framework for Trustworthy Medical Image Segmentation

arXiv Apr 14, 2026
Segmentation models based on deep neural networks demonstrate strong generalization for medical image segmentation. However, they often exhibit overconfidence or underconfidence, leading to unreliable confidence scores for segmentation masks, especia... read more 
Computer Vision and Pattern Recognition

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation

arXiv Apr 14, 2026
Multimodal Large Language Models frequently suffer from inference hallucinations, partially stemming from language priors dominating visual evidence. Existing training-free mitigation methods either perturb the visual representation and deviate from ... read more 
Computation and Language cs.AI cs.CV
Popular Topics
Recent Journals