Small AI models learn to spot cervical spine fractures in radiology reports
A new finetuning method lets small open-weight language models accurately extract acute cervical spine fracture labels from CT reports while ...
A new finetuning method lets small open-weight language models accurately extract acute cervical spine fracture labels from CT reports while ...
A web-based cognitive screening tool for children with intellectual disabilities showed strong test-retest reliability over 45 days in a small ...
A global meta-analysis of 542 observations from 111 studies finds that nitrogen addition synchronously reduces the stability of both aboveground ...
A lean XAI framework combining SHAP, SHAPTime, and rolling-origin validation delivers stable, horizon-aware explanations for supply-chain demand forecasts on the ...
Researchers have combined YOLOv12 detection, capsule networks, reinforcement learning, and Harris Hawks Optimization into a real-time face detection framework that ...
A new reliability-centred framework shows that frame-wise tracking accuracy alone fails to capture how faithfully AI pose estimation preserves downstream ...
A new study testing three AI relighting systems and interviewing film professionals finds the technology works best as a selective ...
A new audit protocol reveals that machine learning models trained on cheap proxy labels for cryptocurrency risk can excel at ...
A 13-year fully factorial experiment manipulating carbon dioxide, nitrogen, warming, and reduced rainfall shows that grassland stability is governed by ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine