SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models
SpatialCORE uses grounding confidence as a reward so vision-language models reason from accurately localized objects.
1 stories, newest first · one card per story
SpatialCORE uses grounding confidence as a reward so vision-language models reason from accurately localized objects.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views