Embodied-R1.5：通过具身基础模型演化物理智能
Embodied-R1.5是一个统一具身基础模型，将具身认知、任务规划、纠错与指向能力整合在单一架构中。基于三条自动化数据构建流水线，团队搭建超过150亿模型token的数据系统，并设计多任务平衡强化学习方案以缓解异构任务冲突。其Planner-Grounder-Corrector闭环框架使模型能在长周期任务中自主执行并自我纠正。仅8B参数的Embodied-R1.5在24个具身VLM基准中的16个上达到SOTA，超越Gemini-Robotics-ER-1.5与GPT-5.4，并可微调为VLA，在4个操作任务基准上领先π_{0.5}等模型。零样本真实机器人实验验证了其指令遵循、可操作物体判别、铰接物体操控与长周期复杂任务中的泛化能力。模型权重、数据集、训练代码及评估框架EmbodiedEvalKit已开源。
仅8B参数就在24项具身视觉语言基准上赢过GPT-5.4和Gemini-Robotics，还把模型权重、训练代码全开源了，做具身智能的团队不跟进就是犯罪。
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
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 $\pi_{0.5}$ 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.
| Comments: | Embodied R1.5 technical report. Project page: this https URL |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2606.11324 [cs.RO] |
| (or arXiv:2606.11324v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2606.11324 arXiv-issued DOI via DataCite |
Submission history
From: Yifu Yuan [view email]
[v1]
Tue, 9 Jun 2026 18:07:50 UTC (26,600 KB)
[v2]
Sat, 11 Jul 2026 14:44:40 UTC (26,601 KB)
来源：HuggingFace Daily Papers（社区热门论文） · arxiv.org