Artificial Intelligence Medical Compendium

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

Showing 39,431 to 39,440 of 223,737 articles

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation

arXiv Mar 23, 2026
Recent advances in text-to-image (T2I) generation via reinforcement learning (RL) have benefited from reward models that assess semantic alignment and visual quality. However, most existing reward models pay limited attention to fine-grained spatial ... read more 
Computer Vision and Pattern Recognition cs.AI

Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration

arXiv Mar 23, 2026
The process of discovery requires active exploration -- the act of collecting new and informative data. However, efficient autonomous exploration remains a major unsolved problem. The dominant paradigm addresses this challenge by using Reinforcement ... read more 
Machine Learning

Repurposing Geometric Foundation Models for Multi-view Diffusion

arXiv Mar 23, 2026
While recent advances in generative latent spaces have driven substantial progress in single-image generation, the optimal latent space for novel view synthesis (NVS) remains largely unexplored. In particular, NVS requires geometrically consistent ge... read more 
Computer Vision and Pattern Recognition

The Dual Mechanisms of Spatial Reasoning in Vision-Language Models

arXiv Mar 23, 2026
Many multimodal tasks, such as image captioning and visual question answering, require vision-language models (VLMs) to associate objects with their properties and spatial relations. Yet it remains unclear where and how such associations are computed... read more 
Computer Vision and Pattern Recognition cs.LG

UniMotion: A Unified Framework for Motion-Text-Vision Understanding and Generation

arXiv Mar 23, 2026
We present UniMotion, to our knowledge the first unified framework for simultaneous understanding and generation of human motion, natural language, and RGB images within a single architecture. Existing unified models handle only restricted modality s... read more 
Computer Vision and Pattern Recognition cs.AI

End-to-End Training for Unified Tokenization and Latent Denoising

arXiv Mar 23, 2026
Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be trained in the... read more 
Computer Vision and Pattern Recognition cs.AI cs.GR cs.LG

Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework

arXiv Mar 23, 2026
Full-waveform inversion (FWI) estimates physical parameters in the wave equation from limited measurements and has been widely applied in geophysical exploration, medical imaging, and non-destructive testing. Conventional FWI methods are limited by t... read more 
Machine Learning cs.AI physics.geo-ph

SynLeaF: A Dual-Stage Multimodal Fusion Framework for Synthetic Lethality Prediction Across Pan- and Single-Cancer Contexts

arXiv Mar 23, 2026
Accurate prediction of synthetic lethality (SL) is important for guiding the development of cancer drugs and therapies. SL prediction faces significant challenges in the effective fusion of heterogeneous multi-source data. Existing multimodal methods... read more 
Genomics cs.AI cs.LG

Abnormalities and Disease Detection in Gastro-Intestinal Tract Images

arXiv Mar 23, 2026
Gastrointestinal (GI) tract image analysis plays a crucial role in medical diagnosis. This research addresses the challenge of accurately classifying and segmenting GI images for real-time applications, where traditional methods often struggle due to... read more 
Image and Video Processing cs.AI cs.CV

Instruction-Tuned, but Not More Verifiable Instruction-Following: A Cross-Task Diagnosis for LoRA Adapters

arXiv Mar 23, 2026
Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized cross-task capabi... read more 
Machine Learning cs.AI cs.CL
Popular Topics
Recent Journals