We systematically study the impact of 3D-informed data, architecture, and training setups and present SpatialLLM, an LMM with advanced 3D spatial reasoning abilities.
Wufei Ma1
Luoxin Ye1
Celso M de Melo2
Alan Yuille1
Jieneng Chen1
1Johns Hopkins University
2DEVCOM Army Research Laboratory
We systematically study the impact of 3D-informed data, architecture, and training setups and present SpatialLLM, an LMM with advanced 3D spatial reasoning abilities.
@inproceedings{ma2025spatialllm,
title={SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models},
author={Ma, Wufei and Ye, Luoxin and de Melo, Celso and Yuille, Alan L and Chen, Jieneng},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
year={2025}
}
This website template is adapted from Image Sculpting.