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.
Spatialrgpt: Grounded spatial reasoning in vision-language models.Advances in Neural Information Processing Systems, 37:135062–135093
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.CV 4years
2026 4representative citing papers
Proposes an equation-anchored tool-use method for MLLMs that writes the pinhole back-projection equation in Chain-of-Thought and substitutes retrieved camera intrinsics and depths to achieve robustness in 3D object detection and visual grounding under rescaled intrinsics.
HoloCount is a three-tier visual counting benchmark showing that MLLMs fail systematically on analytical reasoning, high-density scenes, and linguistic prior conflicts, with even the best models dropping below 50% accuracy on dense counting.
DepthVLM converts a standard VLM into a dense metric depth predictor by attaching a lightweight head and training under unified vision-text supervision, outperforming prior VLMs and some pure vision models on a new indoor-outdoor benchmark.
citing papers explorer
-
HoloCount: A Holistic Visual Counting Benchmark for MLLMs
HoloCount is a three-tier visual counting benchmark showing that MLLMs fail systematically on analytical reasoning, high-density scenes, and linguistic prior conflicts, with even the best models dropping below 50% accuracy on dense counting.