Article

EmbodiedMidtrain: Bridging the gap between vision-language models and VLAs via mid-training

The paper proposes EmbodiedMidtrain, which bridges the gap between vision-language models (VLMs) and vision-language-action models (VLAs) through mid-training. The authors first characterize the data distribution gap between the two, finding that VLA data occupy compact regions largely separated from the VLM distribution. They then build a mid-training data engine that uses a lightweight learnable proximity estimator to select the candidates most aligned with VLA from a large VLM pool, producing the EmbodiedMidtrain-1M dataset for mid-training VLMs.

Part of the event: Proposes a training data method for EmbodiedMidtrain

This page provides a summary and source link only.