Artificial Intelligence Medical Compendium

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

Showing 33,741 to 33,750 of 221,422 articles

HQF-Net: A Hybrid Quantum-Classical Multi-Scale Fusion Network for Remote Sensing Image Segmentation

arXiv Apr 8, 2026
Remote sensing semantic segmentation requires models that can jointly capture fine spatial details and high-level semantic context across complex scenes. While classical encoder-decoder architectures such as U-Net remain strong baselines, they often ... read more 
Computer Vision and Pattern Recognition cs.AI

Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning

arXiv Apr 8, 2026
Although Multimodal Large Language Models have achieved remarkable progress, they still struggle with complex 3D spatial reasoning due to the reliance on 2D visual priors. Existing approaches typically mitigate this limitation either through computat... read more 
Computer Vision and Pattern Recognition

URMF: Uncertainty-aware Robust Multimodal Fusion for Multimodal Sarcasm Detection

arXiv Apr 8, 2026
Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have improved MSD through cross-modal interaction and incongruity reasoning, they often assume that all mod... read more 
Computer Vision and Pattern Recognition cs.AI cs.MM

DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting

arXiv Apr 8, 2026
Sparse-view reconstruction with 3D Gaussian Splatting (3DGS) is fundamentally ill-posed due to insufficient geometric supervision, often leading to severe overfitting and the emergence of structural distortions and translucent haze-like artifacts. Wh... read more 
Computer Vision and Pattern Recognition

LiveStre4m: Feed-Forward Live Streaming of Novel Views from Unposed Multi-View Video

arXiv Apr 8, 2026
Live-streaming Novel View Synthesis (NVS) from unposed multi-view video remains an open challenge in a wide range of applications. Existing methods for dynamic scene representation typically require ground-truth camera parameters and involve lengthy ... read more 
Computer Vision and Pattern Recognition

How Well Do Vision-Language Models Understand Sequential Driving Scenes? A Sensitivity Study

arXiv Apr 8, 2026
Vision-Language Models (VLMs) are increasingly proposed for autonomous driving tasks, yet their performance on sequential driving scenes remains poorly characterized, particularly regarding how input configurations affect their capabilities. We intro... read more 
Computer Vision and Pattern Recognition

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching

arXiv Apr 8, 2026
Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We challenge this paradigm by asking whether all modalities, including textual descriptions, spatial layouts,... read more 
Computer Vision and Pattern Recognition

FlowExtract: Procedural Knowledge Extraction from Maintenance Flowcharts

arXiv Apr 8, 2026
Maintenance procedures in manufacturing facilities are often documented as flowcharts in static PDFs or scanned images. They encode procedural knowledge essential for asset lifecycle management, yet inaccessible to modern operator support systems. Vi... read more 
Computer Vision and Pattern Recognition cs.AI

Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization

arXiv Apr 8, 2026
Recent advancements in Multimodal Large Language Models (MLLMs) have incentivized models to ``think with images'' by actively invoking visual tools during multi-turn reasoning. The common Reinforcement Learning (RL) practice of relying on outcome-bas... read more 
Computer Vision and Pattern Recognition

Instance-Adaptive Parametrization for Amortized Variational Inference

arXiv Apr 8, 2026
Latent variable models, including variational autoencoders (VAE), remain a central tool in modern deep generative modeling due to their scalability and a well-founded probabilistic formulation. These models rely on amortized variational inference to ... read more 
Machine Learning cs.AI
Popular Topics
Recent Journals