Paper page - HuGe: Scaling Humanoid Generalist Vision-Language-Action Models with Egocentric Experience

Source: https://huggingface.co/papers/2610.34186 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

HuGe pre-trains vision-language-action models on egocentric human and robot data with pseudo-proprioception and visual adaptation to enable whole-body humanoid control.

ExtendingVision-Language-Action models(VLAs) to humanoid robots requires coordinated whole-body control and diverse demonstrations that are costly to collect in real-world scenarios. Although egocentric human demonstrations provide a complementary source of task experience, differences in visual embodiment and missing robot proprioception complicate transfer to humanoid policies. To address these challenges, we introduce HuGe, a family of Humanoid GeneralistVLAspre-trained on over 2,000 hours of egocentric human and robot data. Specifically, HuGe employs three existing representative VLA architectures to predictlatent motion tokensfor a pretrainedwhole-body controller, together with hand-control signals. Based on this, we introduce a three-stage training pipeline that combinesegocentric pre-training,humanoid adaptation, and downstream fine-tuning. To facilitate transfer across embodiments, we constructpseudo-proprioceptive statesthrough simulation playback during pre-training and modify arm appearance in egocentric observations throughre-renderingduring downstream fine-tuning. With this pipeline, HuGe achieves the state-of-the-art on simulation benchmark HumanoidArena. Furthermore, real-world experiments on the Unitree G1 indicate that augmenting robot demonstrations with visually adapted egocentric demonstrations significantly increases success on a pick-and-drop task.

View arXiv pageView PDFProject pageGitHub11Add to collection

Get this paper in your agent:

hf papers read 2610\.34186

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.34186 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.34186 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.34186 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.