STARE is a 4K-task benchmark showing multimodal LLMs perform near random chance on multi-step spatial simulation tasks such as cube net folding and tangrams, despite strong 2D transformation results.
Simulation as an engine of physical scene understanding.Proceedings of the National Academy of Sciences, 110(45):18327–18332
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations
STARE is a 4K-task benchmark showing multimodal LLMs perform near random chance on multi-step spatial simulation tasks such as cube net folding and tangrams, despite strong 2D transformation results.