Update model card for yolo11-det

README.md

@@ -110,9 +110,12 @@ Row conventions in the table below:
 | Medium | ONNX FP16 (CUDA) | 65.90% | -0.01 | 49.55% | 22.09 | 28.59 | 152.0 | [v-708](https://edgefirst.studio/public/validation/v-708/details?mode=charts) |
 | Medium | macOS CoreML — Neural Engine (FP16) | 64.73% | -1.18 | 48.53% | 18.47 | 22.51 | 104.0 | [v-761](https://edgefirst.studio/public/validation/v-761/details?mode=charts) |
 | Medium | macOS CoreML — Metal GPU (FP16) | 64.75% | -1.16 | 48.59% | 40.41 | 44.71 | 72.0 | [v-76b](https://edgefirst.studio/public/validation/v-76b/details?mode=charts) |
+| Medium | NXP i.MX 8M Plus + VeriSilicon NPU | 50.85% | -15.06 ⚠ | 35.38% | 333.96 | 367.36 | 3.0 | [v-794](https://edgefirst.studio/public/validation/v-794/details?mode=charts) |
+| Medium | NXP i.MX 8M Plus + VeriSilicon NPU | 53.75% | -12.16 ⚠ | 39.48% | 327.98 | 377.23 | 3.0 | [v-780](https://edgefirst.studio/public/validation/v-780/details?mode=charts) |
 | Medium | Raspberry Pi 5 + Hailo-8L NPU | 62.87% | -3.04 | 47.03% | 70.72 | 81.73 | 14.0 | [v-76e](https://edgefirst.studio/public/validation/v-76e/details?mode=charts) |
 | Medium | NVIDIA Jetson Orin Nano (TensorRT FP16) | 65.88% | -0.03 | 49.56% | 50.81 | 63.11 | 78.0 | [v-762](https://edgefirst.studio/public/validation/v-762/details?mode=charts) |
 
+> **⚠ Below expectations — under investigation.** The rows marked ⚠ above measure more than 10 percentage points below the same training session's float reference: the model accuracy on that platform is below our expectations. We publish the measured numbers rather than hiding them, and we are investigating the results to make improvements — the next snapshot of this card will reflect any recovered accuracy.
 
 
 ---