SATURN reconstructs approximate 3D scenes, derives soft perspective-aware predicates, and executes them symbolically to achieve stable performance on complex multi-perspective spatial grounding tasks where VLMs degrade.
An empirical analysis on spatial reasoning capabilities of large multimodal models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
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.
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
VLMs reach only 0.66 accuracy on relative camera pose estimation while humans achieve 0.91 and specialized pipelines reach 0.99, exposing weaknesses in multi-view spatial reasoning.
citing papers explorer
-
SATURN: Symbolic Spatial Reasoning for Multi-Perspective Grounding
SATURN reconstructs approximate 3D scenes, derives soft perspective-aware predicates, and executes them symbolically to achieve stable performance on complex multi-perspective spatial grounding tasks where VLMs degrade.
-
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.
-
Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs
Introduces CausalPhys benchmark with causal graphs and CRFT fine-tuning to improve VLMs' causal physical reasoning accuracy and interpretability.
-
Lost in Space? Vision-Language Models Struggle with Relative Camera Pose Estimation
VLMs reach only 0.66 accuracy on relative camera pose estimation while humans achieve 0.91 and specialized pipelines reach 0.99, exposing weaknesses in multi-view spatial reasoning.