| title | Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models |
|---|---|
| authors | Yifu Yuan, Yaoting Huang, Xianze Yao, Yutong Li, Shuoheng Zhang, Linqi Han, Pengyi Li, Jiangeng Sun, Wenting Jia, Zhao Zhang, Yuhao Liu, Ruihao Liao, Yucheng Hu, Qiyu Wu, Yuxiao Li, Zibin Dong, Fei Ni, Yan Zheng, Shuyang Gu, Yi Ma, Hongyao Tang, Han Hu, Jianye Hao |
| date | 2026-06-09 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.11324 |
| upvotes | 28 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| primer | Vision-language-action models |
| abstract | We introduce Embodied-R1.5, a unified Embodied Foundation Model (EFM) that integrates comprehensive embodied reasoning capabilities, spanning embodied cognition, task planning, correction, and pointing, within a single architecture toward general physical intelligence. Leveraging three automated data construction pipelines to significantly expand the data coverage of critical capabilities, we build a large-scale data system of over 15B tokens, and design a multi-task balanced RL recipe to alleviate heterogeneous task conflicts. We further introduce a Planner-Grounder-Corrector (PGC) closed-loop framework that enables a single model to autonomously execute and self-correct over long-horizon tasks. With only 8B parameters, Embodied-R1.5 achieves SOTA on 16 out of 24 embodied VLM benchmarks, surpassing leading models like Gemini-Robotics-ER-1.5 and GPT-5.4. Benefiting from the internalized embodied capabilities, Embodied-R1.5 can be fine-tuned into a VLA with only a small amount of data, outperforming leading VLA models like π_{0.5} across 4 popular manipulation benchmark suites. We further conduct extensive zero-shot real-robot experiments, validating performance in instruction following, affordance grounding, articulated object manipulation, and long-horizon complex tasks, demonstrating strong generalization to the physical world. We open-source model weights, datasets, training code, and EmbodiedEvalKit, an evaluation framework tailored for embodied tasks, to facilitate future research in EFMs. |
cite
@misc{yuan2026embodied,
title={Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models},
author={Yifu Yuan and Yaoting Huang and Xianze Yao and Yutong Li and Shuoheng Zhang and Linqi Han and Pengyi Li and Jiangeng Sun and Wenting Jia and Zhao Zhang and Yuhao Liu and Ruihao Liao and Yucheng Hu and Qiyu Wu and Yuxiao Li and Zibin Dong and Fei Ni and Yan Zheng and Shuyang Gu and Yi Ma and Hongyao Tang and Han Hu and Jianye Hao},
year={2026},
eprint={2606.11324},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.11324}
}