EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data

2026-02-18

AI Summary

This work addresses the challenge of transferring high-DoF dexterous manipulation skills to robots by leveraging large-scale human behavioral data. Building upon 20,854 hours of egocentric human action videos, the authors develop a vision–language–action (VLA) model and introduce a lightweight two-stage transfer strategy: pretraining on human data followed by fine-tuning with a small amount of aligned human–robot demonstration data. They report the first empirical observation of a log-linear scaling law between human data volume and validation loss, which strongly correlates with real-world robotic performance. Evaluated on a 22-DoF dexterous hand, the approach achieves a 54% average improvement in task success rate over non-pretrained baselines and successfully generalizes to lower-DoF robotic hands, demonstrating that large-scale human data can serve as a reusable, embodiment-agnostic prior for robotic motor skills.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Large Vision Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Human behavior is among the most scalable sources of data for learning physical intelligence, yet how to effectively leverage it for dexterous manipulation remains unclear. While prior work demonstrates human to robot transfer in constrained settings, it is unclear whether large scale human data can support fine grained, high degree of freedom dexterous manipulation. We present EgoScale, a human to dexterous manipulation transfer framework built on large scale egocentric human data. We train a Vision Language Action (VLA) model on over 20,854 hours of action labeled egocentric human video, more than 20 times larger than prior efforts, and uncover a log linear scaling law between human data scale and validation loss. This validation loss strongly correlates with downstream real robot performance, establishing large scale human data as a predictable supervision source. Beyond scale, we introduce a simple two stage transfer recipe: large scale human pretraining followed by lightweight aligned human robot mid training. This enables strong long horizon dexterous manipulation and one shot task adaptation with minimal robot supervision. Our final policy improves average success rate by 54% over a no pretraining baseline using a 22 DoF dexterous robotic hand, and transfers effectively to robots with lower DoF hands, indicating that large scale human motion provides a reusable, embodiment agnostic motor prior.

Problem

• dexterous manipulation
• egocentric human data
• human to robot transfer
• physical intelligence
• scaling

Innovation

• EgoScale
• dexterous manipulation
• egocentric human data
• vision-language-action model
• scaling law