Artificial Intelligence Medical Compendium

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

Showing 56,611 to 56,620 of 226,846 articles

Revisiting Diffusion Model Predictions Through Dimensionality

arXiv
Recent advances in diffusion and flow matching models have highlighted a shift in the preferred prediction target -- moving from noise ($\varepsilon$) and velocity (v) to direct data (x) prediction -- particularly in high-dimensional settings. Howeve... read more 

MultiModal Fine-tuning with Synthetic Captions

arXiv
In this paper, we address a fundamental gap between pre-training and fine-tuning of deep neural networks: while pre-training has shifted from unimodal to multimodal learning with enhanced visual understanding, fine-tuning predominantly remains unimod... read more 

Accurate Network Traffic Matrix Prediction via LEAD: an LLM-Enhanced Adapter-Based Conditional Diffusion Model

arXiv
Driven by the evolution toward 6G and AI-native edge intelligence, network operations increasingly require predictive and risk-aware adaptation under stringent computation and latency constraints. Network Traffic Matrix (TM), which characterizes flow... read more 

Variance & Greediness: A comparative study of metric-learning losses

arXiv
Metric learning is central to retrieval, yet its effects on embedding geometry and optimization dynamics are not well understood. We introduce a diagnostic framework, VARIANCE (intra-/inter-class variance) and GREEDINESS (active ratio and gradient no... read more 

Hypernetwork-Based Adaptive Aggregation for Multimodal Multiple-Instance Learning in Predicting Coronary Calcium Debulking

arXiv
In this paper, we present the first attempt to estimate the necessity of debulking coronary artery calcifications from computed tomography (CT) images. We formulate this task as a Multiple-instance Learning (MIL) problem. The difficulty of this task ... read more 

SimGraph: A Unified Framework for Scene Graph-Based Image Generation and Editing

arXiv
Recent advancements in Generative Artificial Intelligence (GenAI) have significantly enhanced the capabilities of both image generation and editing. However, current approaches often treat these tasks separately, leading to inefficiencies and challen... read more 

HERS: Hidden-Pattern Expert Learning for Risk-Specific Vehicle Damage Adaptation in Diffusion Models

arXiv
Recent advances in text-to-image (T2I) diffusion models have enabled increasingly realistic synthesis of vehicle damage, raising concerns about their reliability in automated insurance workflows. The ability to generate crash-like imagery challenges ... read more 

Sustainable Materials Discovery in the Era of Artificial Intelligence

arXiv
Artificial intelligence (AI) has transformed materials discovery, enabling rapid exploration of chemical space through generative models and surrogate screening. Yet current AI workflows optimize performance first, deferring sustainability to post sy... read more 

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

arXiv
Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates a significant latency bottleneck. Existing solutions face a dichotomy:... read more 

Bi-Anchor Interpolation Solver for Accelerating Generative Modeling

arXiv
Flow Matching (FM) models have emerged as a leading paradigm for high-fidelity synthesis. However, their reliance on iterative Ordinary Differential Equation (ODE) solving creates a significant latency bottleneck. Existing solutions face a dichotomy:... read more