Update README.md

README.md

@@ -35,7 +35,7 @@ A **pi0.5 (π₀.₅)** Vision-Language-Action (VLA) model, finetuned on the **L
 - **Framework:** OpenTau
 
 ### Architecture
-The pi0.5 architecture uses a flow-matching-based policy designed for open-world generalization. It combines a Visual Language Model (VLM) for high-level semantic understanding with a smaller "action expert" model that generates continuous joint trajectories (50-step action chunks) via flow matching.
+The pi0.5 architecture uses a flow-matching-based policy designed for open-world generalization. It combines a Visual Language Model (VLM) for high-level semantic understanding with a smaller "action expert" model that generates continuous joint trajectories (10-step action chunks) via flow matching.
 
 ---
 
@@ -46,7 +46,7 @@ This model was finetuned on the **LIBERO** benchmark dataset. The LIBERO suite c
 - **Spatial Generalization** (libero_spatial)
 - **Object Generalization** (libero_object)
 - **Goal Generalization** (libero_goal)
-- **Long-Horizon Tasks** (libero_100)
+- **Long-Horizon Tasks** (libero_10)
 
 ### Results
 For detailed usage instructions, success rates, baseline comparisons, and evaluation protocols, please refer to the [OpenTau GitHub Repository](https://github.com/TensorAuto/OpenTau).