# DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs

- Source: arXiv cs.RO
- Published: 2026-10-21T04:00:00.000Z
- RoboHot: https://robohot.news/en/items/g6eobaz53fwuwqakc37132c2g
- Original: https://arxiv.org/abs/2605.19294

## Summary

DEFLECT is an offline post-training framework that turns the temporal gap between prediction and execution into preference supervision, enabling policies to produce actions aligned with the execution-time state even when their inputs are stale.