Artificial Intelligence Medical Compendium

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

Showing 63,651 to 63,660 of 230,801 articles

LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning

arXiv Jan 15, 2026
Current multimodal latent reasoning often relies on external supervision (e.g., auxiliary images), ignoring intrinsic visual attention dynamics. In this work, we identify a critical Perception Gap in distillation: student models frequently mimic a te... read more 
Computer Vision and Pattern Recognition cs.AI

Step-by-Step Causality: Transparent Causal Discovery with Multi-Agent Tree-Query and Adversarial Confidence Estimation

arXiv Jan 15, 2026
Causal discovery aims to recover ``what causes what'', but classical constraint-based methods (e.g., PC, FCI) suffer from error propagation, and recent LLM-based causal oracles often behave as opaque, confidence-free black boxes. This paper introduce... read more 
Machine Learning cs.AI stat.ML

MHub.ai: A Simple, Standardized, and Reproducible Platform for AI Models in Medical Imaging

arXiv Jan 15, 2026
Artificial intelligence (AI) has the potential to transform medical imaging by automating image analysis and accelerating clinical research. However, research and clinical use are limited by the wide variety of AI implementations and architectures, i... read more 
Artificial Intelligence cs.CV cs.ET cs.LG cs.SE

RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation

arXiv Jan 15, 2026
Open-vocabulary 3D Scene Graph (3DSG) generation can enhance various downstream tasks in robotics, such as manipulation and navigation, by leveraging structured semantic representations. A 3DSG is constructed from multiple images of a scene, where ob... read more 
Computer Vision and Pattern Recognition cs.AI cs.RO

Bias in the Shadows: Explore Shortcuts in Encrypted Network Traffic Classification

arXiv Jan 15, 2026
Pre-trained models operating directly on raw bytes have achieved promising performance in encrypted network traffic classification (NTC), but often suffer from shortcut learning-relying on spurious correlations that fail to generalize to real-world d... read more 
Machine Learning cs.NI

From Physical Degradation Models to Task-Aware All-in-One Image Restoration

arXiv Jan 15, 2026
All-in-one image restoration aims to adaptively handle multiple restoration tasks with a single trained model. Although existing methods achieve promising results by introducing prompt information or leveraging large models, the added learning module... read more 
Computer Vision and Pattern Recognition

ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and TEst-time Generative Adaptation

arXiv Jan 15, 2026
We introduce ELITE, an Efficient Gaussian head avatar synthesis from a monocular video via Learned Initialization and TEst-time generative adaptation. Prior works rely either on a 3D data prior or a 2D generative prior to compensate for missing visua... read more 
Computer Vision and Pattern Recognition

Robust and Generalizable Atrial Fibrillation Detection from ECG Using Time-Frequency Fusion and Supervised Contrastive Learning

arXiv Jan 15, 2026
Atrial fibrillation (AF) is a common cardiac arrhythmia that significantly increases the risk of stroke and heart failure, necessitating reliable and generalizable detection methods from electrocardiogram (ECG) recordings. Although deep learning has ... read more 
Quantitative Methods

Cell Behavior Video Classification Challenge, a benchmark for computer vision methods in time-lapse microscopy

arXiv Jan 15, 2026
The classification of microscopy videos capturing complex cellular behaviors is crucial for understanding and quantifying the dynamics of biological processes over time. However, it remains a frontier in computer vision, requiring approaches that eff... read more 
Image and Video Processing cs.CV q-bio.QM

DanQing: An Up-to-Date Large-Scale Chinese Vision-Language Pre-training Dataset

arXiv Jan 15, 2026
Vision-Language Pre-training (VLP) models demonstrate strong performance across various downstream tasks by learning from large-scale image-text pairs through contrastive pretraining. The release of extensive English image-text datasets (e.g., COYO-7... read more 
Computer Vision and Pattern Recognition cs.AI
Popular Topics
Recent Journals