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.
hub
Spatialcot: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning.arXiv preprint arXiv:2501.10074, 2025a
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 13roles
background 4polarities
background 4representative citing papers
ESI-Bench shows active exploration outperforms passive observation in multimodal LLMs on spatial tasks but reveals failures from poor action choices and overconfident belief commitment unlike humans.
4DThinker enables VLMs to perform dynamic spatial reasoning by thinking with 4D latent mental imagery using new fine-tuning and reinforcement learning methods.
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
SCP defines a new benchmark task for predicting spatial causal outcomes beyond direct observation and shows that 23 leading models lag far behind humans on it.
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
Proxy3D generates efficient 3D proxy representations via semantic clustering from video frames and aligns them to VLMs through multi-stage training on the new SpaceSpan dataset, achieving competitive performance on 3D VQA, grounding, and spatial benchmarks with shorter sequences.
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 while staying far smaller.
DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.
Introduces a trustworthiness-and-complexity switching metric that lets LLMs choose between language and grid modalities for spatial reasoning, yielding up to 42% gains in tested settings.
GR3D is a VLM that combines explicit 2D, implicit 2D, and monocular 3D grounding mechanisms to improve performance on spatial understanding benchmarks.
Hybrid vision-language and geometric optimization framework generates editable minimal surfaces from sketches, reporting 0.844 topological similarity on 100 test sketches.
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.
citing papers explorer
-
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.
-
ESI-Bench: Towards Embodied Spatial Intelligence that Closes the Perception-Action Loop
ESI-Bench shows active exploration outperforms passive observation in multimodal LLMs on spatial tasks but reveals failures from poor action choices and overconfident belief commitment unlike humans.
-
4DThinker: Thinking with 4D Imagery for Dynamic Spatial Understanding
4DThinker enables VLMs to perform dynamic spatial reasoning by thinking with 4D latent mental imagery using new fine-tuning and reinforcement learning methods.
-
Token Warping Helps MLLMs Look from Nearby Viewpoints
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
-
SCP: Spatial Causal Prediction in Video
SCP defines a new benchmark task for predicting spatial causal outcomes beyond direct observation and shows that 23 leading models lag far behind humans on it.
-
SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images
SpatialForge synthesizes 10 million spatial QA pairs from in-the-wild 2D images to train VLMs for better depth ordering, layout, and viewpoint-dependent reasoning.
-
Proxy3D: Efficient 3D Representations for Vision-Language Models via Semantic Clustering and Alignment
Proxy3D generates efficient 3D proxy representations via semantic clustering from video frames and aligns them to VLMs through multi-stage training on the new SpaceSpan dataset, achieving competitive performance on 3D VQA, grounding, and spatial benchmarks with shorter sequences.
-
Spatio-Temporal Grounding of Large Language Models from Perception Streams
FESTS uses Spatial Regular Expressions compiled from queries to generate 27k training tuples that raise a 3B-parameter LLM's frame-level F1 on spatio-temporal video reasoning from 48.5% to 87.5%, matching GPT-4.1 while staying far smaller.
-
DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models
DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.
-
Spatial Reasoning via Modality Switching Between Language and Symbolic Representation
Introduces a trustworthiness-and-complexity switching metric that lets LLMs choose between language and grid modalities for spatial reasoning, yielding up to 42% gains in tested settings.
-
Grounded 3D-Aware Spatial Vision-Language Modeling
GR3D is a VLM that combines explicit 2D, implicit 2D, and monocular 3D grounding mechanisms to improve performance on spatial understanding benchmarks.
-
Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches
Hybrid vision-language and geometric optimization framework generates editable minimal surfaces from sketches, reporting 0.844 topological similarity on 100 test sketches.
-
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
The paper provides the first comprehensive survey of multimodal chain-of-thought reasoning, including foundational concepts, a taxonomy of methodologies, application analyses, challenges, and future directions.