Artificial Intelligence Medical Compendium

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

Showing 30,651 to 30,660 of 220,177 articles

HiProto: Hierarchical Prototype Learning for Interpretable Object Detection Under Low-quality Conditions

arXiv
Interpretability is essential for deploying object detection systems in critical applications, especially under low-quality imaging conditions that degrade visual information and increase prediction uncertainty. Existing methods either enhance image ... read more 

Reward Design for Physical Reasoning in Vision-Language Models

arXiv
Physical reasoning over visual inputs demands tight integration of visual perception, domain knowledge, and multi-step symbolic inference. Yet even state-of-the-art Vision Language Models (VLMs) fall far short of human performance on physics benchmar... read more 

Remote Sensing Image Super-Resolution for Imbalanced Textures: A Texture-Aware Diffusion Framework

arXiv
Generative diffusion priors have recently achieved state-of-the-art performance in natural image super-resolution, demonstrating a powerful capability to synthesize photorealistic details. However, their direct application to remote sensing image sup... read more 

Depth-Aware Image and Video Orientation Estimation

arXiv
This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed method estimates the orientation based on the depth distribution across different quadrants of the imag... read more 

Log-based vs Graph-based Approaches to Fault Diagnosis

arXiv
Modern distributed systems generate large volumes of logs that can be analyzed to support essential AIOps tasks such as fault diagnosis, which plays a crucial role in maintaining system reliability. Most existing approaches rely on log-based models t... read more 

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

arXiv
Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understanding and interacting with the physical world. While traditional methods achieve high fidelity, they are limi... read more 

ROSE: Retrieval-Oriented Segmentation Enhancement

arXiv
Existing segmentation models based on multimodal large language models (MLLMs), such as LISA, often struggle with novel or emerging entities due to their inability to incorporate up-to-date knowledge. To address this challenge, we introduce the Novel... read more 

Seedance 2.0: Advancing Video Generation for World Complexity

arXiv
Seedance 2.0 is a new native multi-modal audio-video generation model, officially released in China in early February 2026. Compared with its predecessors, Seedance 1.0 and 1.5 Pro, Seedance 2.0 adopts a unified, highly efficient, and large-scale arc... read more 

Machine learning recovers folk classification of Banisteriopsis caapi from herbarium leaves an ayahuasca liana.

iScience
Ayahuasca refers to an entheogenic brew and its main vine, Banisteriopsis caapi, whose high morphological diversity underlies traditional folk classifications. This study evaluated whether machine learning algorithms can recover folk classifications ... read more 

From pathogenesis to precision medicine in systemic lupus erythematosus: Emerging biomarkers and targeted interventions.

iScience
Systemic lupus erythematosus (SLE) is a chronic, systemic autoimmune disease characterized by immune dysregulation, autoantibody production, and chronic inflammation, which can potentially damage almost any organ. The estimated worldwide prevalence o... read more