align format

README.md

@@ -14,10 +14,10 @@ tags:
 ## Brief Introduction
 
 **Vista** is a generalizable driving world model that is capable of:
-- **High-Fidelity Future Prediction:** Predict high-fidelity futures in various scenarios.
-- **Coherent Long-Horizon Rollout:** Extend its predictions to continuous and long horizons.
-- **Versatile Action Controllability:** Execute multi-modal actions (steering angles, speeds, commands, trajectories, goal points).
-- **Generalizable Reward Function:** Provide rewards for different actions without accessing ground truth actions.
+- **High-Fidelity Future Prediction:** *Predict high-fidelity futures in various scenarios*.
+- **Coherent Long-Horizon Rollout:** *Extend its predictions to continuous and long horizons*.
+- **Versatile Action Controllability:** *Execute multi-modal actions (steering angles, speeds, commands, trajectories, goal points)*.
+- **Generalizable Reward Function:** *Provide rewards for different actions without accessing ground truth actions*.
 
 ## Related Links