We are open-sourcing WorldCompass, an RL post-training framework specifically designed for Interactive World Models.
🛠️ Open Training Code: Fully customizable for post-training with your own data, rewards, or base models.
⚡ Open-source Checkpoint: More precise instruction-following for complex, compositional action inputs.
WorldCompass significantly improves compositional action following and long-horizon interaction in HY-World 1.5.
🕹️ Play now: https://t.co/0awf2D5LaT
⭐ GitHub:
An open RL post-training stack for interactive world models means you can tune action-following on your own rewards and data rather than accepting a vendor checkpoint's behavior.
