Spatial-SSRL-81k

📖Paper| 🏠Github |🤗Spatial-SSRL-7B Model | 🤗Spatial-SSRL-3B Model | 🤗Spatial-SSRL-Qwen3VL-4B Model | 🤗Spatial-SSRL-81k Dataset | 📰Daily Paper

Spatial-SSRL-81k is a training dataset for enhancing spatial understanding in large vision-language models. It contains 81,053 samples of five pretext tasks for self-supervised learning, offering simple, intrinsic supervision that scales RLVR efficiently.

📢 News

• 🚀 [2026/04/05] We have released the training code of Spatial-SSRL.
• 🚀 [2026/02/25] We have released the 🤗Spatial-SSRL-3B Model, initialized from Qwen2.5-VL-3B-Instruct.
• 🚀 [2026/02/21] Our work has been accepted by CVPR 2026.
• 🚀 [2025/11/24] We have released the 🤗Spatial-SSRL-Qwen3VL-4B Model, initialized from Qwen3-VL-4B-Instruct.
• 🚀 [2025/11/03] Now you can try out Spatial-SSRL-7B on 🤗Spatial-SSRL Space.
• 🚀 [2025/11/03] We have released the 🤗Spatial-SSRL-7B Model, and 🤗Spatial-SSRL-81k Dataset.
• 🚀 [2025/11/02] We have released the 🏠Spatial-SSRL Repository.

🌈 Overview

We are thrilled to introduce Spatial-SSRL, a novel self-supervised RL paradigm aimed at enhancing LVLM spatial understanding. By optimizing Qwen2.5-VL-7B with Spatial-SSRL, the model exhibits stronger spatial intelligence across seven spatial understanding benchmarks in both image and video settings.

Spatial-SSRL is a lightweight tool-free framework that is natually compatible with the RLVR training paradigm and easy to extend to a multitude of pretext tasks. Five tasks are currently formulated in the framework, requiring only ordinary RGB and RGB-D images. And we welcome you to join Spatial-SSRL with effective pretext tasks to further strengthen the capabilities of LVLMs!

💡 Highlights

• 🔥 Highly Scalable: Spatial-SSRL uses ordinary raw RGB and RGB-D images instead of richly-annotated public datasets or manual labels for data curation, making it highly scalable.
• 🔥 Cost-effective: Avoiding the need for human labels or API calls for general LVLMs throughout the entire pipeline endows Spatial-SSRL with cost-effectiveness.
• 🔥 Lightweight: Prior approaches for spatial understanding heavily rely on annotation of external tools, incurring inherent errors in training data and additional cost. In constrast, Spatial-SSRL is completely tool-free and can easily be extended to more self-supervised tasks.
• 🔥 Naturally Verifiable: Intrinsic supervisory signals determined by pretext objectives are naturally verifiable, aligning Spatial-SSRL well with the RLVR paradigm.

🖼️ Task examples

🛠️ Usage

You can find all question-answering pairs in spatialssrl.parquet and the images in images.zip. The images are organized in five folders, each corresponding to a 2D or 3D pretext task. See the formulation of each task in 📖Paper if you are interested.

✒️Citation

If you find this dataset useful, please kindly cite:

@article{liu2025spatial,
  title={Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning},
  author={Liu, Yuhong and Zhang, Beichen and Zang, Yuhang and Cao, Yuhang and Xing, Long and Dong, Xiaoyi and Duan, Haodong and Lin, Dahua and Wang, Jiaqi},
  journal={arXiv preprint arXiv:2510.27606},
  year={2025}
}

📄 License

Usage and License Notices: The data and code are intended and licensed for research use only.