SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
Spatial reasoning with vision-language models in ego-centric multi-view scenes
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10roles
background 2polarities
background 2representative citing papers
SpatialWorld is a new multi-simulator benchmark showing top multimodal agents achieve under 18% success on interactive spatial tasks requiring active exploration and long-horizon planning.
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.
OmniSpace is a plug-and-play method that improves spatial reasoning in MLLMs for AV by injecting camera pose, using epipolar attention across views, and distilling 3D geometric knowledge to overcome weak cross-view correspondence and depth estimation.
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
SpatialSV trains MLLMs to lift 2D visual features into explicit 3D representations via task-oriented supervision for interpretable spatial awareness.
OpenWorldLib defines world models as perception-centered systems with interaction and long-term memory, and provides a modular inference codebase unifying interactive video, 3D, reasoning, and VLA tasks.
citing papers explorer
-
SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
-
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
SpatialWorld is a new multi-simulator benchmark showing top multimodal agents achieve under 18% success on interactive spatial tasks requiring active exploration and long-horizon planning.
-
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.
-
OmniSpace: Efficient Geometry Awareness for Autonomous Vehicles MLLMs
OmniSpace is a plug-and-play method that improves spatial reasoning in MLLMs for AV by injecting camera pose, using epipolar attention across views, and distilling 3D geometric knowledge to overcome weak cross-view correspondence and depth estimation.
-
CVSBench: A Comprehensive Benchmark for Cross-view Spatial Reasoning and Dreaming
CVSBench benchmark shows VLMs struggle with cross-view spatial consistency but improve substantially when given 3D scene imagination inputs.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
EgoDyn-Bench: Evaluating Ego-Motion Understanding in Vision-Centric Foundation Models for Autonomous Driving
EgoDyn-Bench finds a Perception Bottleneck: foundation models hold ego-motion logic in language but misalign it with vision, underperforming geometric baselines until given explicit trajectories.
-
Feeling the Space: Egomotion-Aware Video Representation for Efficient and Accurate 3D Scene Understanding
Motion-MLLM integrates IMU egomotion data into MLLMs using cascaded filtering and asymmetric fusion to ground visual content in physical trajectories for scale-aware 3D understanding, achieving competitive accuracy at higher speed.
-
SpatialSV: Internalizing Interpretable 3D Spatial Awareness in MLLMs via Task-Oriented Visual Supervision
SpatialSV trains MLLMs to lift 2D visual features into explicit 3D representations via task-oriented supervision for interpretable spatial awareness.
-
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
OpenWorldLib defines world models as perception-centered systems with interaction and long-term memory, and provides a modular inference codebase unifying interactive video, 3D, reasoning, and VLA tasks.