THU-SI / Spatial-MLLM
[NeurIPS 2025 Spotlight] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
Why this job: works in the areas we cover, but does not say which job it does


What it does
- 🎉[01/05/2026] We release two new SFT models. Spatial-MLLM-v1.1-Instruct-135K and Spatial-MLLM-v1.1-Instruct-820K.
- 🎉[01/05/2026] We refactor our repo and release the refined SFT training code for Spatial-MLLM-v1.1-Instruct. We also release code for space-aware frame sampling.
- 🎉[05/30/2025] We release Spatial-MLLM-subset-sft, which is trained on a subset of our proposed Spatial-MLLM-120k dataset. We also release the evaluation code on VSI-Bench. Please switch to the v1.0 branch for instructions and code related t
- 🔥[05/30/2025] We release "Spatial-MLLM. Boosting MLLM Capabilities in Visual-based Spatial Intelligence". Check our project page and arXiv paper.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Inactive
- Last commit 9 months ago
- Stars
- 497
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 72% closed
- 8 still open
- Pull requests
- 0 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| Gorilla-Lab-SCUT / PaDT | 167 | 3 months ago | Apache-2.0 | No downloads |
| worldbench / LiDARCrafter | 207 | 11 months ago | MIT | No downloads |
| FoundationVision / Liquid | 641 | 5 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 96%
- Shell 4%
Topics
- llm
- multimodal
- multimodal-large-language-models
- spatial-intelligence
- aigc
Project record
- JobOther AI tools
- StatusListed
- Commits26
- Forks17
- Watching6
- Stars in 28 days+4
- CreatedMay 29, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026
