# CondenseVLA: Improving Multi-Frame VLA Policy Efficiency with Learnable History Compression

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/e7mhpqvlep68k16ls732h8d7a
- Original: https://arxiv.org/abs/2610.25927

## Summary

CondenseVLA proposes adding a learnable history compression module to the decoding side of VLA policies. It uses learnable queries and multi-head cross-attention to distill the per-frame features cached by the VLM backbone into a fixed number of slot tokens, and applies auxiliary regularization that penalizes overlap among slot attention maps and decorrelates slot embeddings to reduce redundancy.