EO-1: An Open Unified Embodied Foundation Model for General Robot Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qu, Delin, Song, Haoming, Chen, Qizhi, Chen, Zhaoqing, Gao, Xianqiang, Wang, Dong, Ye, Xinyi, Lv, Qi, Shi, Modi, Ren, Guanghui, Ruan, Cheng, Yao, Maoqing, Yang, Haoran, Bao, Jiacheng, Zhao, Bin, Li, Xuelong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910032242671616
author Qu, Delin
Song, Haoming
Chen, Qizhi
Chen, Zhaoqing
Gao, Xianqiang
Wang, Dong
Ye, Xinyi
Lv, Qi
Shi, Modi
Ren, Guanghui
Ruan, Cheng
Yao, Maoqing
Yang, Haoran
Bao, Jiacheng
Zhao, Bin
Li, Xuelong
author_facet Qu, Delin
Song, Haoming
Chen, Qizhi
Chen, Zhaoqing
Gao, Xianqiang
Wang, Dong
Ye, Xinyi
Lv, Qi
Shi, Modi
Ren, Guanghui
Ruan, Cheng
Yao, Maoqing
Yang, Haoran
Bao, Jiacheng
Zhao, Bin
Li, Xuelong
contents The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, we introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models. Project Page: https://eo-robotics.ai/eo-1.
format Preprint
id arxiv_https___arxiv_org_abs_2508_21112
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EO-1: An Open Unified Embodied Foundation Model for General Robot Control
Qu, Delin
Song, Haoming
Chen, Qizhi
Chen, Zhaoqing
Gao, Xianqiang
Wang, Dong
Ye, Xinyi
Lv, Qi
Shi, Modi
Ren, Guanghui
Ruan, Cheng
Yao, Maoqing
Yang, Haoran
Bao, Jiacheng
Zhao, Bin
Li, Xuelong
Robotics
Artificial Intelligence
The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general purpose embodied intelligent systems. Recent vision-language-action (VLA) models, which are co-trained on large-scale robot and visual-text data, have demonstrated notable progress in general robot control. However, they still fail to achieve human-level flexibility in interleaved reasoning and interaction. In this work, we introduce EO-Robotics, consists of EO-1 model and EO-Data1.5M dataset. EO-1 is a unified embodied foundation model that achieves superior performance in multimodal embodied reasoning and robot control through interleaved vision-text-action pre-training. The development of EO-1 is based on two key pillars: (i) a unified architecture that processes multimodal inputs indiscriminately (image, text, video, and action), and (ii) a massive, high-quality multimodal embodied reasoning dataset, EO-Data1.5M, which contains over 1.5 million samples with emphasis on interleaved vision-text-action comprehension. EO-1 is trained through synergies between auto-regressive decoding and flow matching denoising on EO-Data1.5M, enabling seamless robot action generation and multimodal embodied reasoning. Extensive experiments demonstrate the effectiveness of interleaved vision-text-action learning for open-world understanding and generalization, validated through a variety of long-horizon, dexterous manipulation tasks across multiple embodiments. This paper details the architecture of EO-1, the data construction strategy of EO-Data1.5M, and the training methodology, offering valuable insights for developing advanced embodied foundation models. Project Page: https://eo-robotics.ai/eo-1.
title EO-1: An Open Unified Embodied Foundation Model for General Robot Control
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2508.21112