# IG-VLA: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination

- Source: arXiv cs.RO
- Published: 2026-10-27T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/mf7qyed7w131k5abyk16e9zad
- Original: https://arxiv.org/abs/2610.02626

## Summary

The authors propose the IG-VLA framework, which lets a vision-language-action model imagine task-relevant future scene evolution in visual representation space and internalize the reasoning results into a compact Scene Gist Token via Scene Gist Memory, thereby skipping explicit future imagination at inference time.