Artificial Intelligence Medical Compendium

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

Showing 45,451 to 45,460 of 224,055 articles

Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning

arXiv Mar 2, 2026
Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However, measuring info... read more 
Computer Vision and Pattern Recognition cs.AI

DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks

arXiv Mar 2, 2026
Mixture-of-Experts (MoE) architectures have emerged as a powerful paradigm for scaling neural networks while maintaining computational efficiency. However, standard MoE implementations rely on two rigid design assumptions: (1) fixed Top-K routing whe... read more 
Machine Learning cs.AI

Towards Principled Dataset Distillation: A Spectral Distribution Perspective

arXiv Mar 2, 2026
Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic counterparts for efficient model training. However, existing DD methods exhibit substantial performance degradation on long-tailed datasets. We identify two fundam... read more 
Computer Vision and Pattern Recognition cs.AI

Dual Distillation for Few-Shot Anomaly Detection

arXiv Mar 2, 2026
Anomaly detection is a critical task in computer vision with profound implications for medical imaging, where identifying pathologies early can directly impact patient outcomes. While recent unsupervised anomaly detection approaches show promise, the... read more 
Computer Vision and Pattern Recognition

Preoperative-to-intraoperative Liver Registration for Laparoscopic Surgery via Latent-Grounded Correspondence Constraints

arXiv Mar 2, 2026
In laparoscopic liver surgery, augmented reality technology enhances intraoperative anatomical guidance by overlaying 3D liver models from preoperative CT/MRI onto laparoscopic 2D views. However, existing registration methods lack explicit modeling o... read more 
Computer Vision and Pattern Recognition

Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration

arXiv Mar 2, 2026
Recently, significant breakthroughs have been made in all-in-one image restoration (AiOIR), which can handle multiple restoration tasks with a single model. However, existing methods typically focus on a specific image domain, such as natural scene, ... read more 
Computer Vision and Pattern Recognition

Shape-Interpretable Visual Self-Modeling Enables Geometry-Aware Continuum Robot Control

arXiv Mar 2, 2026
Continuum robots possess high flexibility and redundancy, making them well suited for safe interaction in complex environments, yet their continuous deformation and nonlinear dynamics pose fundamental challenges to perception, modeling, and control. ... read more 
Robotics cs.AI cs.LG eess.SY

Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence

arXiv Mar 2, 2026
Motivation: Sparse autoencoders (SAEs) decompose foundation model activations into interpretable features, but causal feature-to-feature interactions across network depth remain unknown for biological foundation models. Results: We introduce causal... read more 
Machine Learning q-bio.CB q-bio.GN

NeuroSymb-MRG: Differentiable Abductive Reasoning with Active Uncertainty Minimization for Radiology Report Generation

arXiv Mar 2, 2026
Automatic generation of radiology reports seeks to reduce clinician workload while improving documentation consistency. Existing methods that adopt encoder-decoder or retrieval-augmented pipelines achieve progress in fluency but remain vulnerable to ... read more 
Computer Vision and Pattern Recognition

StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models

arXiv Mar 2, 2026
Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales predominantly refin... read more 
Computer Vision and Pattern Recognition
Popular Topics
Recent Journals