Upload README.md with huggingface_hub

README.md

@@ -134,6 +134,22 @@ python run_pi05.py --server wss://YOUR-POD-8000.proxy.runpod.net
 python run_pi05.py --server wss://YOUR-POD-8000.proxy.runpod.net --no-jpeg
 ```
 
+## External Videos (Phone Capture)
+
+Real-world demonstrations recorded externally during evaluation runs:
+
+### JPEG Compression (~270ms)
+![External Video - JPEG](external_jpeg.gif)
+*External phone recording showing smooth robot control with JPEG compression*
+
+### Raw Images (~600ms)
+![External Video - Raw](external_raw.gif)
+*Same task without compression - noticeably slower/choppier control*
+
+### Edge Retrieval (Out-of-Distribution)
+![External Video - Edge](external_edge.gif)
+*Ball placed at workspace edge - a position that appeared in <10% of training episodes*
+
 ## Comparison with ACT Policy
 
 Trained on the same dataset:
@@ -141,9 +157,19 @@ Trained on the same dataset:
 | Policy | Architecture | Inference | Grasp | Generalization |
 |--------|-------------|-----------|-------|----------------|
 | **Pi0.5** | VLA (3B params) | Remote GPU | ✅ | ✅ Edge positions |
-| ACT | Transformer (25M) | Local | ✅ | ⚠️ Center only |
+| ACT | Transformer (25M) | Local | ✅ | ❌ Center only |
+
+### Edge Retrieval: Pi0.5 vs ACT
+
+**ACT failed at edge positions** - the policy was only trained with ~72 episodes where the ball was mostly in the center/reachable area. When the ball was placed at the edge of the workspace, ACT would miss or fail to reach it entirely.
+
+**Pi0.5 succeeds at edge positions** despite having the same training data. This demonstrates the power of VLA pre-training:
+
+1. **SigLIP** (vision encoder) was pre-trained on billions of images - understands "ball" and "edge" concepts generally
+2. **Gemma** (language model) provides semantic grounding - "pick up ball" applies regardless of position
+3. **Action Expert** learned smooth motion primitives from diverse robot arms during base model training
 
-**Key advantage:** Pi0.5 successfully picks up ball from edge positions that ACT couldn't handle - demonstrates better generalization from VLA pre-training.
+The base Pi0.5 model was trained on data from many different robot arms performing various tasks. This gives it a strong prior on reachable workspace and arm kinematics that ACT (trained from scratch) simply doesn't have.
 
 ## Infrastructure Notes