Spatial Vision-Language Models

9 repos

Vision-language models and frameworks designed to understand and reason about spatial relationships, geometry, and 3D scene understanding. This cluster covers VLM architectures optimized for spatial intelligence tasks, along with curated resources and benchmarks for evaluating spatial reasoning capabilities in multimodal AI systems. The core focus is enabling language models to process visual information with geometric and spatial awareness.

Python · 6
spatial-reasoning ·677
spatial-intelligence ·642
vision-language-model ·491
vlm ·475
awesome-spatial-vlms ·472
survey ·472
mllm ·472
awesome-list ·472
vision-language-models ·183
benchmark ·180