DriveSpatial benchmark shows the strongest of 15 VLMs trails humans by 28.4 points on spatiotemporal tasks, with cognitive scene construction as the primary weakness.
Spatialbot: Precise spatial understanding with vision language models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 4roles
dataset 1polarities
baseline 1representative citing papers
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
OmniView-Space framework with MPSM, tool-guided reasoning, and distillation achieves SOTA on spatial reasoning benchmarks for MLLMs while reducing external geometry dependencies.
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.
citing papers explorer
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the strongest of 15 VLMs trails humans by 28.4 points on spatiotemporal tasks, with cognitive scene construction as the primary weakness.
-
SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
-
OmniView-Space: Reinforcing Spatial Reasoning via Multi-Perspective Spatial Mapping
OmniView-Space framework with MPSM, tool-guided reasoning, and distillation achieves SOTA on spatial reasoning benchmarks for MLLMs while reducing external geometry dependencies.
-
Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.