Artificial Intelligence Medical Compendium

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

Showing 45,161 to 45,170 of 224,055 articles

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

arXiv Mar 3, 2026
Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution encoder features into the decoder. However, these skip pathways also ... read more 
Computer Vision and Pattern Recognition

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection

arXiv Mar 3, 2026
Medical image segmentation commonly relies on U-shaped encoder-decoder architectures such as U-Net, where skip connections preserve fine spatial detail by injecting high-resolution encoder features into the decoder. However, these skip pathways also ... read more 
Computer Vision and Pattern Recognition

Specificity-aware reinforcement learning for fine-grained open-world classification

arXiv Mar 3, 2026
Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and specific. Recent reasoning Large Multimodal Models (LMMs) exhibit strong visual understanding capability ... read more 
Computer Vision and Pattern Recognition

Specificity-aware reinforcement learning for fine-grained open-world classification

arXiv Mar 3, 2026
Classifying fine-grained visual concepts under open-world settings, i.e., without a predefined label set, demands models to be both accurate and specific. Recent reasoning Large Multimodal Models (LMMs) exhibit strong visual understanding capability ... read more 
Computer Vision and Pattern Recognition

SynthCharge: An Electric Vehicle Routing Instance Generator with Feasibility Screening to Enable Learning-Based Optimization and Benchmarking

arXiv Mar 3, 2026
The electric vehicle routing problem with time windows (EVRPTW) extends the classical VRPTW by introducing battery capacity constraints and charging station decisions. Existing benchmark datasets are often static and lack verifiable feasibility, whic... read more 
Machine Learning cs.AI

Guiding Sparse Neural Networks with Neurobiological Principles to Elicit Biologically Plausible Representations

arXiv Mar 3, 2026
While deep neural networks (DNNs) have achieved remarkable performance in tasks such as image recognition, they often struggle with generalization, learning from few examples, and continuous adaptation - abilities inherent in biological neural system... read more 
Machine Learning

UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?

arXiv Mar 3, 2026
Unified multimodal models have recently demonstrated strong generative capabilities, yet whether and when generation improves understanding remains unclear. Existing benchmarks lack a systematic exploration of the specific tasks where generation faci... read more 
Computer Vision and Pattern Recognition cs.AI

Beyond Language Modeling: An Exploration of Multimodal Pretraining

arXiv Mar 3, 2026
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models remains opaque. We provide empirical clarity through controlled, from-s... read more 
Computer Vision and Pattern Recognition

CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance

arXiv Mar 3, 2026
Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called CFG-Ctrl, which reinterprets CFG as a control applied to the first-... read more 
Computer Vision and Pattern Recognition cs.LG

AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis

arXiv Mar 3, 2026
Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three challenges: restricted access to proprietary data, unsafe action execut... read more 
Machine Learning cs.AI
Popular Topics
Recent Journals