DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
Spatialvlm: Endowing vision-language models with spatial reasoning capabilities
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
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.
AssemLM uses a specialized point cloud encoder inside a multimodal LLM to reach state-of-the-art 6D pose prediction for assembly tasks, backed by a new 900K-sample benchmark called AssemBench.
citing papers explorer
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
Unlocking Dense Metric Depth Estimation in VLMs
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.
-
AssemLM: Spatial Reasoning Multimodal Large Language Models for Robotic Assembly
AssemLM uses a specialized point cloud encoder inside a multimodal LLM to reach state-of-the-art 6D pose prediction for assembly tasks, backed by a new 900K-sample benchmark called AssemBench.