Astra-WM

Astra-WM is not used as an open-ended image generator. It receives context images and a natural-language camera-motion instruction, then synthesizes a novel observation that should stay consistent with the same scene. This makes the simulator a mechanism for controlled visual intervention: the policy changes its perceptual input by choosing an action, then judges whether the imagined observation provides useful spatial evidence.

Checkpoint

This checkpoint is used as an external world simulator tool for agentic spatial reasoning. Given context images and a camera movement instruction, it generates the corresponding novel- view observation image.

Files

• ema.safetensors: model weights
• ae.safetensors: autoencoder weights
• config.json: BAGEL model config
• llm_config.json: language model config
• vit_config.json: vision encoder config
• tokenizer and preprocessor files