State of Spatial Reasoning

5 papers · avg viability 4.4

vision-language modelsview selection agentspatial reasoning3D environmentsChain-of-View promptingLLMOpenEQAScanQASQA3D

Top papers

World2Mind: Cognition Toolkit for Allocentric Spatial Reasoning in Foundation Models(7.0)
Grid Spatial Understanding: A Dataset for Textual Spatial Reasoning over Grids, Embodied Settings, and Coordinate Structures(5.0)
m2sv: A Scalable Benchmark for Map-to-Street-View Spatial Reasoning(4.0)
RieMind: Geometry-Grounded Spatial Agent for Scene Understanding(3.0)
CoV: Chain-of-View Prompting for Spatial Reasoning(3.0)