S
Spatial-MLLM
THU-SI/Spatial-MLLM
[NeurIPS 2025 Spotlight] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence
★482stars
Python
MIT
Updated: 2d ago
📋 Project at a Glance
Tap to expand
What's this?A open-source Models project, built with Python, focusing on aigc and llm
Who made it?Maintained by THU-SI team, 482⭐ on GitHub, #1852 out of 3201 in Models
Why does it exist?With the growing demand for aigc and llm in Models, THU-SI created Spatial-MLLM as a streamlined solution.
What can it do?Key use cases: multimodal, multimodal-large-language-models, spatial-intelligence
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/THU-SI/Spatial-MLLM | 官网 https://diankun-wu.github.io/Spatial-MLLM/
🔗 github.com/THU-SI/Spatial-MLLM | 官网 https://diankun-wu.github.io/Spatial-MLLM/
Topics
aigcllmmultimodalmultimodal-large-language-modelsspatial-intelligence