# From Predictive Geometry to Action: Learning Complementary Predictive Representations for Embodied Manipulation

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/t3ap4qz1y8521gf472yakp27j
- Original: https://arxiv.org/abs/2610.28164

## Summary

The paper proposes a two-stage framework that learns complementary predictive representations from multi-view video clips to enhance embodied manipulation policies. In the pretraining stage, a frozen 3D foundation model provides dense geometric features, which are compressed into predictive geometric representations and optimized to preserve scene structure and its temporal evolution; action supervision is then applied to geometric transitions to extract a motor representation that emphasizes action-relevant transitions. In the downstream post-training stage, predictive geometry is transferred through geometry queries, and the motor representation guides intermediate features along the action-generation pathway. Future observations serve only as privileged supervision during training and are not needed at inference time.