Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids

Roger Sala Sisó, Tiago Silvério, Jakob Sand, Tran Nguyen Le|July 22, 2026arXiv

Key Takeaway

Deploying VLA robots in the real world is primarily a systems integration problem—thoughtful data curation, control alignment, and targeted fine-tuning on a single GPU can turn a failing policy into a working one.

Summary

This paper presents DEED, a practical framework for deploying vision-language-action (VLA) robots in real retail environments.

training applications efficiency

Key Terms

vision-language-action-model post-training distribution-shift data-curation embodied-agent