MolmoAct2

MolmoAct2 is an open vision-language-action model for robot control. It builds on Molmo2-ER, an embodied-reasoning VLM backbone, and connects the autoregressive VLM to a flow-matching continuous action expert through per-layer key-value cache conditioning.

This checkpoint is the post-trained, multi-embodiment MolmoAct2 model. It is intended as a foundation checkpoint for further robot fine-tuning rather than as a ready-to-run policy for a single deployment setting.

Quick Links

• 📂 Models: Models, Finetuned Models
• 📂 Datasets: MolmoAct2-BimanualYAM Dataset, MolmoAct2 Datasets, Molmo2-ER Datasets
• 📄 Paper:
• 💻 Code: allenai/molmoact2
• 🎥 Blog Post: MolmoAct2

Intended Use

Use this checkpoint for further fine-tuning on a target robot embodiment or benchmark. It contains the VLM and continuous action expert weights, plus normalization metadata for the post-training mixture in norm_stats.json.

This model card intentionally does not include direct policy inference code. For ready-to-run inference examples, use one of the fine-tuned checkpoints such as MolmoAct2-LIBERO, MolmoAct2-DROID, MolmoAct2-BimanualYAM, or MolmoAct2-SO100_101.

Model and Hardware Safety

MolmoAct2 generate robot actions from visual observations and language instructions, but their behavior may vary across embodiments, environments, and hardware configurations. Users should carefully validate model outputs before deployment, especially when operating physical robots or other actuated systems. Where possible, actions should be monitored through interpretable intermediate outputs (adaptive depth map), simulation rollouts, action limits, or other safety checks before execution on hardware. The model’s action space should be bounded by the training data, robot controller limits, and task-specific safety constraints, including limits on speed, workspace, torque, and contact force. Users should follow the hardware manufacturer’s safety guidelines, use appropriate emergency-stop mechanisms, and operate the system only in a safely configured environment with human supervision.

Citation

@misc{fang2026molmoact2actionreasoningmodels,
      title={MolmoAct2: Action Reasoning Models for Real-world Deployment}, 
      author={Haoquan Fang and Jiafei Duan and Donovan Clay and Sam Wang and Shuo Liu and Weikai Huang and Xiang Fan and Wei-Chuan Tsai and Shirui Chen and Yi Ru Wang and Shanli Xing and Jaemin Cho and Jae Sung Park and Ainaz Eftekhar and Peter Sushko and Karen Farley and Angad Wadhwa and Cole Harrison and Winson Han and Ying-Chun Lee and Eli VanderBilt and Rose Hendrix and Suveen Ellawela and Lucas Ngoo and Joyce Chai and Zhongzheng Ren and Ali Farhadi and Dieter Fox and Ranjay Krishna},
      year={2026},
      eprint={2605.02881},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2605.02881}, 
}