SPATIALQUERY-1M adds a 1.06M-pair closest-instance metric spatial reasoning benchmark, and SPATIALQUERY answers it by grounding geometry and prompting a VLM with a bird's-eye-view abstraction.
Guiding long-horizon task and motion planning with vision language models,
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
2026 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models
SPATIALQUERY-1M adds a 1.06M-pair closest-instance metric spatial reasoning benchmark, and SPATIALQUERY answers it by grounding geometry and prompting a VLM with a bird's-eye-view abstraction.