Artificial Intelligence Medical Compendium

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

Showing 19,351 to 19,360 of 214,800 articles

Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement

arXiv May 12, 2026
Large Vision-Language Models (LVLMs) have achieved remarkable performance on diverse vision-language tasks. However, LVLMs still suffer from hallucinations, generating text that contradicts the visual input. Existing research has primarily focused on... read more 
Computer Vision and Pattern Recognition

RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition

arXiv May 12, 2026
Recent diffusion-based approaches have made substantial progress in image layer decomposition. However, accurately decomposing complex natural images remains challenging due to difficulties in occlusion completion, robust layer disentanglement, and p... read more 
Computer Vision and Pattern Recognition

REFNet++: Multi-Task Efficient Fusion of Camera and Radar Sensor Data in Bird's-Eye Polar View

arXiv May 12, 2026
A realistic view of the vehicle's surroundings is generally offered by camera sensors, which is crucial for environmental perception. Affordable radar sensors, on the other hand, are becoming invaluable due to their robustness in variable weather con... read more 
Computer Vision and Pattern Recognition cs.AI

Bin Latent Transformer (BiLT): A shift-invariant autoencoder for calibration-free spectral unmixing of turbid media

arXiv May 12, 2026
The accurate recovery of constituent-level optical properties from integrating sphere measurements is a central analytical challenge in pharmaceutical analysis, food science, and biomedical diagnostics. Neural network autoencoders can extract spectra... read more 
Optics cs.LG eess.SP physics.med-ph

Selection, Not Fusion: Radar-Modulated State Space Models for Radar-Camera Depth Estimation

arXiv May 12, 2026
Radar-camera depth estimation must turn an ultra-sparse, all-weather, metric radar signal into a dense per-pixel depth map. Existing methods -- concatenation, confidence-aware gating, sparse supervision, graph-based extraction -- combine radar and im... read more 
Computer Vision and Pattern Recognition

Martingale-Consistent Self-Supervised Learning

arXiv May 12, 2026
Self-supervised learning (SSL) is often deployed under changing information, such as shorter histories, missing features, or partially observed images. In these settings, predictions from coarse and refined views should be coherent: before refinement... read more 
Machine Learning cs.AI

UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs

arXiv May 12, 2026
Multimodal large language models are increasingly expected to perform thinking with images, yet existing visual latent reasoning methods still rely on explicit textual chain-of-thought interleaved with visual latent tokens. This interleaved design li... read more 
Computer Vision and Pattern Recognition cs.CL

Very Efficient Listwise Multimodal Reranking for Long Documents

arXiv May 12, 2026
Listwise reranking is a key yet computationally expensive component in vision-centric retrieval and multimodal retrieval-augmented generation (M-RAG) over long documents. While recent VLM-based rerankers achieve strong accuracy, their practicality is... read more 
Information Retrieval cs.AI cs.CV cs.MM

When Brains Disagree: Biological Ambiguity Underlies the Challenge of Amyloid PET Synthesis from Structural MRI

arXiv May 12, 2026
Structural MRI-to-amyloid PET synthesis has been proposed as a non-invasive alternative for amyloid assessment in Alzheimer's disease (AD). However, reported performance of identical models varies widely across studies, and increasingly complex archi... read more 
Computer Vision and Pattern Recognition

Few-Shot Synthetic Data Generation with Diffusion Models for Downstream Vision Tasks

arXiv May 12, 2026
Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic data augmenta... read more 
Computer Vision and Pattern Recognition
Popular Topics
Recent Journals