Jul 2026
Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
It is demonstrated that training models with chain-of-thought supervision over the authors' hierarchical sub-tasks, combined with reinforcement learning with verifiable rewards, significantly improves both spatial consistency across sub-tasks and target-task accuracy, supporting the value of the proposed decomposition as both a diagnostic tool and a training signal.
Patrick Rim, Tom Long, Ekta Prashnani et al.
· arXiv.org · 0 citations