Awesome Spatial Intelligence in VLMs

This carefully curated list brings together key methods, datasets, and benchmarks in the field of spatial intelligence for VLMs.

With the development of multimodal models, evaluating and enhancing their spatial intelligence has become a key research frontier. This list aims to provide researchers and engineers with a quick index to track the latest advancements in the field.

We welcome contributions of excellent resources you find via Pull Request!

Table of Contents

• Awesome Spatial Intelligence in VLMs
  • Methods
  • Datasets & Benchmarks
  • Findings & Applications

Methods

Visual-based methods

Title	Introduction	Date	Code
Planning with the Views		2026-05	Github
RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		2025-12	Github
N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models		2025-12	Github
SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery		2025-12	Github
Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling		2025-12	Github
CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning		2025-12	-
S2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance		2025-12	-
EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence		2025-12	-
Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation		2025-12	-
Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning		2025-11	Github
G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning		2025-11	Github
Video Spatial Reasoning with Object-Centric 3D Rollout		2025-11	-
Abstract 3D Perception for Spatial Intelligence in Vision-Language Models		2025-11	-
SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models		2025-11	-
Cambrian-S: Towards Spatial Supersensing in Video		2025-11	Github
Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images		2025-11	Github
SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards		2025-11	Github
TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics		2025-10	Github
Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning		2025-10	Github
Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation		2025-10	Github
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views		2025-10	Github
Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks		2025-10	Github
SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models		2025-10	Github
SpaceVista: All-Scale Visual Spatial Reasoning from mm to km		2025-10	Github
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models		2025-09	Github
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model		2025-09	-
3D Aware Region Prompted Vision Language Model		2025-09	Github
UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding		2025-08	Github
SIFThinker: Spatially-Aware Image Focus for Visual Reasoning		2025-08	Github
Enhancing Spatial Reasoning through Visual and Textual Thinking		2025-07	-
MindJourney: Test-Time Scaling with World Models for Spatial Reasoning		2025-07	Github
Struct2D: A Perception-Guided Framework for Spatial Reasoning in Large Multimodal Models		2025-06	Github
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs		2025-06	Github
SpatialLM: Training Large Language Models for Structured Indoor Modeling		2025-06	Github
Spatial Understanding from Videos: Structured Prompts Meet Simulation Data		2025-06	Github
Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing		2025-06	Github
Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces		2025-05	Github
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		2025-05	Github
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors		2025-05	Github
SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models		2025-05	Github
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence		2025-05	Github
STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs		2025-05	Github
VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction		2025-05	Github
LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding		2025-05	-
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning		2025-05	Github
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation		2025-04	Github
Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipe		2025-04	-
SpaceR: Reinforcing MLLMs in Video Spatial Reasoning		2025-04	Github
Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning		2025-04	Github
SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning		2025-04	Github
ROSS3D: Reconstructive Visual Instruction Tuning with 3D-Awareness		2025-04	Github
SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data		2025-04	-
Visual Agentic AI for Spatial Reasoning with a Dynamic API		2025-02	Github
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding		2025-01	Github
SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning		2025-01	Github
LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Model		2024-12	Github
COARSE CORRESPONDENCES Boost Spatial-Temporal Reasoning in Multimodal Language Model		2024-08	Github
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics		2024-06	GitHub
SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models		2024-06	Github
SpatialBot: Precise Spatial Understanding with Vision Language Models		2024-06	Github
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs		2024-04	Github
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors		2024-03	-
Can Transformers Capture Spatial Relations between Objects?		2024-03	Github
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities		2024-01	Github
Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis		2024-01	Github
3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V		2023-12	-

Text-based methods

Title	Introduction	Date	Code
Imagine while Reasoning in Space: Multimodal Visualization-of-Thought		2025-01	-
Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs		2024-11	-
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning		2024-10	-
SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models		2024-06	Github
Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models		2024-02	-
Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark		2024-01	Github

Datasets & Benchmarks

Visual-based data

Title	Introduction	Date	Code
Planning with the Views		2026-05	Github
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?		2026-02	Github
EscherVerse: An Open World Benchmark and Dataset for Teleo-Spatial Intelligence with Physical-Dynamic and Intent-Driven Understanding		2026-1	Github
RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		2025-12	Github
Towards Cross-View Point Correspondence in Vision-Language Models		2025-12	Github
ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints		2025-11	-
Scaling Spatial Intelligence with Multimodal Foundation Models		2025-11	Github
SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition		2025-11	Github
Visual Spatial Tuning		2025-11	Github
Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models		2025-10	Github
DSI-Bench: A Benchmark for Dynamic Spatial Intelligence		2025-10	Github
Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes		2025-10	-
NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions		2025-10	Github
SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs		2025-09	Github
Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes		2025-09	Github
Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture		2025-09	Github
VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning		2025-08	Github
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations		2025-09	Github
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models		2025-08	Github
11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis		2025-08	-
Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting		2025-07	Github
Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models		2025-07	-
SpatialViz-Bench: An MLLM Benchmark for Spatial Visualization		2025-07	Github
Spatial Mental Modeling from Limited Views		2025-06	Github
SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks		2025-06	-
IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering		2025-06	Github
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes		2025-06	Github
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly		2025-06	Github
Can Vision Language Models Infer Human Gaze Direction? A Controlled Study		2025-06	Github
SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence		2025-06	Github
Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations		2025-06	Github
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models		2025-06	Github
InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models		2025-06	-
MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence		2025-05	Github
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		2025-05	Github
Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models		2025-05	Github
SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding		2025-05	Github
MIRAGE:A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence		2025-05	Github
Can Multimodal Large Language Models Understand Spatial Relations		2025-05	Github
Visuospatial Cognitive Assistant		2025-05	Github
Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?		2025-05	Github
Vision language models have difficulty recognizing virtual objects		2025-05	-
ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models		2025-05	Github
Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames		2025-05	-
SITE: towards Spatial Intelligence Thorough Evaluation		2025-05	Github
CameraBench: Towards Understanding Camera Motions in Any Video		2025-04	Github
Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs		2025-04	Github
From Flatland to Space:Teaching Vision-Language Models to Perceive and Reason in 3D		2025-03	Github
MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLM		2025-03	-
Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space		2025-03	Github
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?		2025-03	Github
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models		2025-03	Github
Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models		2025-03	Github
LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?		2025-03	Github
Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models		2025-02	Github
FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks		2025-02	-
iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs		2025-02	Github
Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics		2025-02	-
SAT: Spatial Aptitude Training for Multimodal Language Models		2024-12	Github
SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models		2024-12	Github
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark		2024-12	Github
Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces		2024-12	Github
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics		2024-11	Github
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models		2024-11	-
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos		2024-11	Github
Is ‘Right’ Right? Enhancing Object Orientation Understanding in Multimodal Language Models through Egocentric Instruction Tuning		2024-10	Github
ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models		2024-10	Github
DOES SPATIAL COGNITION EMERGE IN FRONTIER MODELS?		2024-10	-
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities		2024-10	Github
R2D3: Imparting Spatial Reasoning by Reconstructing 3D Scenes from 2D Images		2024-10	Github
Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models		2024-09	Github
Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?		2024-09	-
VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs		2024-07	Github
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models		2024-06	Github
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners		2024-06	Github
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models		2024-06	Github
GSR-Bench: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs		2024-06	-
Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning		2024-05	Github
Visually Descriptive Language Model for Vector Graphics Reasoning		2024-04	-
SQA3D: Situated Question Answering in 3D Scenes		2022-10	Github
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals		2022-03	Github
SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings		2020-03	Github

Text-based data

Title	Introduction	Date	Code
Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning		2024-12	-
GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning		2024-07	-

Findings

Title	Introduction	Date	Code
Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks		2025-10	Github
How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective		2025-09	Github
Has GPT-5 Achieved Spatial Intelligence? An Empirical Study		2025-08	-
A Call for New Recipes to Enhance Spatial Reasoning in MLLMs		2025-03	Github
Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas		2025-03	Github
Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models		2025-03	Github

Applications

Title	Introduction	Date	Code
Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model		2025-10	Github
SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models		2025-05	-
InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning		2025-05	Github
EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks		2025-03	-
SOFAR: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation		2025-02	Github
ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning		2025-03	Github
VL-Nav: Real-time Vision-Language Navigation with Spatial Reasoning		2025-02	-
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models		2025-01	Github
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection		2024-12	Github
EMMA-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning		2024-12	Github
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning		2024-04	Github
Improving Vision-and-Language Reasoning via Spatial Relations Modeling		2023-11	-