04:00
2026-05-28
arxiv.org
machine-learning
Not All NVFP4 QAT Recipes Are Equal: How Architecture and Scale Shape Model Quality for Anomaly Segmentation
A study evaluating FP4 quantization-aware training (QAT) for real-time anomaly segmentation in brain tumor detection found that architecture choice, not QAT recipe, most determines model quality. The …