Artificial Intelligence Medical Compendium

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

Showing 51,311 to 51,320 of 225,182 articles

Efficient Segment Anything with Depth-Aware Fusion and Limited Training Data

arXiv Feb 12, 2026
Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on RGB inputs. Recent efficient variants reduce computation but still depend on large-scale training. ... read more 
Computer Vision and Pattern Recognition eess.IV

JEPA-VLA: Video Predictive Embedding is Needed for VLA Models

arXiv Feb 12, 2026
Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs still suffer from low sample efficiency and limited generalization. T... read more 
Computer Vision and Pattern Recognition cs.RO

Free Lunch for Stabilizing Rectified Flow Inversion

arXiv Feb 12, 2026
Rectified-Flow (RF)-based generative models have recently emerged as strong alternatives to traditional diffusion models, demonstrating state-of-the-art performance across various tasks. By learning a continuous velocity field that transforms simple ... read more 
Computer Vision and Pattern Recognition cs.LG

Free Lunch for Stabilizing Rectified Flow Inversion

arXiv Feb 12, 2026
Rectified-Flow (RF)-based generative models have recently emerged as strong alternatives to traditional diffusion models, demonstrating state-of-the-art performance across various tasks. By learning a continuous velocity field that transforms simple ... read more 
Computer Vision and Pattern Recognition cs.LG

Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception

arXiv Feb 12, 2026
Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods alleviate t... read more 
Computer Vision and Pattern Recognition cs.AI cs.CL cs.LG

DiffPlace: Street View Generation via Place-Controllable Diffusion Model Enhancing Place Recognition

arXiv Feb 12, 2026
Generative models have advanced significantly in realistic image synthesis, with diffusion models excelling in quality and stability. Recent multi-view diffusion models improve 3D-aware street view generation, but they struggle to produce place-aware... read more 
Computer Vision and Pattern Recognition cs.RO

SynthRAR: Ring Artifacts Reduction in CT with Unrolled Network and Synthetic Data Training

arXiv Feb 12, 2026
Defective and inconsistent responses in CT detectors can cause ring and streak artifacts in the reconstructed images, making them unusable for clinical purposes. In recent years, several ring artifact reduction solutions have been proposed in the ima... read more 
Computer Vision and Pattern Recognition cs.AI

Synthesis of Late Gadolinium Enhancement Images via Implicit Neural Representations for Cardiac Scar Segmentation

arXiv Feb 12, 2026
Late gadolinium enhancement (LGE) imaging is the clinical standard for myocardial scar assessment, but limited annotated datasets hinder the development of automated segmentation methods. We propose a novel framework that synthesises both LGE images ... read more 
Computer Vision and Pattern Recognition cs.AI

TAVAE: A VAE with Adaptable Priors Explains Contextual Modulation in the Visual Cortex

arXiv Feb 12, 2026
The brain interprets visual information through learned regularities, a computation formalized as probabilistic inference under a prior. The visual cortex establishes priors for this inference, some delivered through established top-down connections ... read more 
Neurons and Cognition cs.AI cs.LG

Are Two LLMs Better Than One? A Student-Teacher Dual-Head LLMs Architecture for Pharmaceutical Content Optimization

arXiv Feb 12, 2026
Large language models (LLMs) are increasingly used to create content in regulated domains such as pharmaceuticals, where outputs must be scientifically accurate and legally compliant. Manual quality control (QC) is slow, error prone, and can become a... read more 
Machine Learning
Popular Topics
Recent Journals