Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/03_four_layer_stack.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -19,9 +19,7 @@ simulation studio. Small enough to read, small enough to run on an MCU-class dev
 
 ## Architecture
 
-```
-input 4  →  dense 16 (ReLU)  →  dense 8 (ReLU)  →  output 6
-```
+![Architecture: 4 → 16 → 8 → 6](assets/01_architecture.png)
 
 | part | meaning |
 |------|---------|
@@ -37,6 +35,9 @@ input 4  →  dense 16 (ReLU)  →  dense 8 (ReLU)  →  output 6
 
 The `.npz` also embeds `meta_json`: the full 572-epoch training history
 (per-class accuracy, loss, angle MAE per epoch), so the training curve is inspectable.
+The plot below is drawn directly from that embedded history:
+
+![Training history](assets/02_training_curve.png)
 
 ## Load and run (NumPy only, no framework)
 
@@ -58,6 +59,11 @@ print(cmd, angle)
 
 ## Where this fits: our 4-layer stack
 
+![NCDTech 4-layer stack](assets/03_four_layer_stack.png)
+
+*(Diagram is in Korean; it is the same figure used on our website, demo video, and
+companion dataset.)*
+
 This model is a **layer-2 artifact** of our stack — an edge neural network verified
 through the 8-stage physics simulation workflow of our robot simulation studio.
 Every stage of that workflow runs self QA/QC (layer 3) and reports through an