# inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and Action

- Source: arXiv cs.RO
- Published: 2026-10-22T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/gj9uvqduai4qa18s5r7iowifg
- Original: https://arxiv.org/abs/2610.28882

## Summary

The paper proposes the inr2action framework, which fits a neural implicit representation to each robot manipulation episode starting from a shared meta-learned initialization; the resulting weight delta serves as memory, with a size that does not vary with episode length and stays fixed from one hundred frames to one hundred thousand frames.