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.
These are images of an object. What is the name of the object?
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
ReVSI rebuilds 3D spatial reasoning benchmarks for VLMs by re-annotating objects and geometry across 381 scenes and creating verified QA pairs that match actual model inputs like 16-64 frames.
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
Embodied-R1 uses a pointing-centric representation and reinforced fine-tuning on a 200K dataset to achieve state-of-the-art results on embodied benchmarks plus 56.2% success in SIMPLEREnv and 87.5% on real XArm tasks without task-specific training.
Multi-SpatialMLLM integrates depth perception, visual correspondence, and dynamic perception into MLLMs via a 27M-sample MultiSPA dataset and benchmark, yielding gains on multi-frame spatial tasks.
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.
-
ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning
ReVSI rebuilds 3D spatial reasoning benchmarks for VLMs by re-annotating objects and geometry across 381 scenes and creating verified QA pairs that match actual model inputs like 16-64 frames.
-
MiMo-Embodied: X-Embodied Foundation Model Technical Report
MiMo-Embodied is a single foundation model that achieves state-of-the-art results on 17 embodied AI benchmarks and 12 autonomous driving benchmarks through multi-stage learning, curated data, and CoT/RL fine-tuning that produces positive cross-domain transfer.
-
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Embodied-R1 uses a pointing-centric representation and reinforced fine-tuning on a 200K dataset to achieve state-of-the-art results on embodied benchmarks plus 56.2% success in SIMPLEREnv and 87.5% on real XArm tasks without task-specific training.
-
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
Multi-SpatialMLLM integrates depth perception, visual correspondence, and dynamic perception into MLLMs via a 27M-sample MultiSPA dataset and benchmark, yielding gains on multi-frame spatial tasks.
- ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop