SpatialASM: Internalizing Active Mentalization for Spatial Reasoning
SpatialASM trains vision-language models to plan viewpoints and imagine scenes, improving accuracy on seven spatial benchmarks.
2 stories, newest first · one card per story
SpatialASM trains vision-language models to plan viewpoints and imagine scenes, improving accuracy on seven spatial benchmarks.
SpatialASM trains vision-language models to plan viewpoints and simulate scenes for spatial reasoning.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views