Artificial Intelligence Medical Compendium

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

Showing 871 to 880 of 213,401 articles

Locality-Aware Density Control for Efficient Gaussian-based Image Representation

arXiv
2D Gaussian Splatting is an attractive direction for image representation due to its explicit formulation, fast rasterization, and favorable decoding efficiency. The representation quality of this paradigm depends on the proper allocation of Gaussian... read more 

Chemical filters for ultra-high-throughput materials screening and generation

arXiv
Generative artificial intelligence is rapidly transforming materials design by enabling de novo exploration of immense chemical spaces. Yet a large proportion of AI-generated compositions remain implausible, violating established chemical principles,... read more 

MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors

arXiv
Classical image correspondence is solved at the level of sparse keypoints or dense pixels, but the systems that consume these matches - object-level mapping, topological navigation, scene-graph maintenance - reason about whole objects. Recent work na... read more 

Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

arXiv
Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structure, especially in fine details, like thin structures and small objects... read more 

MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement

arXiv
Monocular geometry estimation has recently achieved impressive performance across diverse scenes. However, state-of-the-art models still face notable distortion in local 3D structure, especially in fine details, like thin structures and small objects... read more 

Keyframe-Anchored Identity Preservation for Sequential-Action Video Generation

arXiv
Identity-preserving text-to-video generation aims to synthesize a video that accurately follows a textual description while maintaining the recognizability of a user-specified subject throughout. The IPVG26 challenge extends this framework from a sin... read more 

Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links

arXiv
This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best... read more 

SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens

arXiv
Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI... read more 

Benchmarking NACTI Species Recognition in Long-Tailed Regimes

arXiv
As with most ``in the wild'' collections of the natural world, the North America Camera Trap Images (NACTI) dataset exhibits long-tailed class imbalance, with the largest class covering over 50% of its 3.7M images. Building on the PyTorch Wildlife mo... read more 

Colloidal quantum dots and their assemblies for circularly polarized luminescence.

Materials horizons
Circularly polarized luminescence (CPL) has attracted significant attention due to its broad application potential in information encryption, chiral sensing, and advanced optoelectronic technologies. However, the construction of CPL-active materials ... read more