# Spark-0 researchers report robot manipulation gains from touch-based training

_Published Thursday, October 15, 2026 at 11:42 PM EDT · Robotics, AI, Science · Latest · Tier 2 — Notable_

Researchers behind the Spark-0 preprint report that retaining touch information during training raised vision-only task success on Ego Humanoid from 52.5% to 71.7%, compared with training on the same data and compute while discarding touch.

The model learns from image-space contact maps derived from tactile gloves and a 1,000-hour dataset of full-hand human manipulation called HumanTouch. It can operate with vision alone or use touch measurements to guide robot actions.

On SparkArena-Real, where the robot also uses touch during deployment, success rose from 44.0% to 52.0%. The results demonstrate benchmark gains on a single dexterous robot embodiment rather than broad deployment across different robot hardware.

## Sources

- [arXiv Query: search_query=cat:cs.RO&id_list=&start=0&max_results=30](https://arxiv.org/abs/2610.22342v1)

---
Canonical: https://techandbusiness.org/newswire/qh8rpRBxwZ6Zg21n-Le4Ta
Published: 2026-10-16T03:42:03.434Z
Story chronology: 2026-10-15T17:56:17.000Z
Retrieved: 2026-10-16T05:59:15.832Z
Publisher: Tech & Business (techandbusiness.org)