Shadowgraph
TrendingAbout
Sign in

mll-lab-nu/Awesome-Spatial-Intelligence-in-VLM

A paper list for spatial reasoning

786

83 commits

updated Aug 23, 2026

See the code

README

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

Methods

Visual-based methods

TitleIntroductionDateCode

Planning with the Views		image2026-05Github

RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		image2025-12Github

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models		image2025-12Github

SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery		image2025-12Github

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling		image2025-12Github

CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning		image2025-12-

S2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance		image2025-12-

EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence		image2025-12-

Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation		image2025-12-

Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning		image2025-11Github

G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning		image2025-11Github

Video Spatial Reasoning with Object-Centric 3D Rollout		image2025-11-

Abstract 3D Perception for Spatial Intelligence in Vision-Language Models		image2025-11-

SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models		image2025-11-

Cambrian-S: Towards Spatial Supersensing in Video		image2025-11Github

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images		image2025-11Github

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards		image2025-11Github

TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics		image2025-10Github

Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning		image2025-10Github

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation		image2025-10Github

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views		image2025-10Github

Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks		image2025-10Github

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models		image2025-10Github

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km		image2025-10Github
Publish
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models		image2025-09Github
Publish
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model		image2025-09-

3D Aware Region Prompted Vision Language Model		image2025-09Github

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding		image2025-08Github

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning		image2025-08Github

Enhancing Spatial Reasoning through Visual and Textual Thinking		image2025-07-
Publish
MindJourney: Test-Time Scaling with World Models for Spatial Reasoning		image2025-07Github
Publish
Struct2D: A Perception-Guided Framework for Spatial Reasoning in Large Multimodal Models		image2025-06Github
Publish
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs		image2025-06Github
Publish
SpatialLM: Training Large Language Models for Structured Indoor Modeling		image2025-06Github

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data		image2025-06Github

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing		image2025-06Github

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces		image2025-05Github
Publish
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		image2025-05Github
Publish
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors		image2025-05Github
Publish
SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models		image2025-05Github
Publish
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence		image2025-05Github

STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs		image2025-05Github

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction		image2025-05Github

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding		image2025-05-
Publish
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning		image2025-05Github
Publish
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation		image2025-04Github

Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipe		image2025-04-

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning		image2025-04Github

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning		image2025-04Github
Publish
SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning		image2025-04Github
Publish
ROSS3D: Reconstructive Visual Instruction Tuning with 3D-Awareness		image2025-04Github
Publish
SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data		image2025-04-

Visual Agentic AI for Spatial Reasoning with a Dynamic API		image2025-02Github
Publish
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding		image2025-01Github

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning		image2025-01Github
Publish
LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Model		image2024-12Github

COARSE CORRESPONDENCES Boost Spatial-Temporal Reasoning in Multimodal Language Model		image2024-08Github
Star Publish
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics		image2024-06GitHub
Star Publish
SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models		image2024-06Github
Star Publish
SpatialBot: Precise Spatial Understanding with Vision Language Models		image2024-06Github
Publish
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs		image2024-04Github

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors		image2024-03-
Publish
Can Transformers Capture Spatial Relations between Objects?		image2024-03Github
Star Publish
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities		image2024-01Github

Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis		image2024-01Github

3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V		image2023-12-

Text-based methods

TitleIntroductionDateCode

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought		image2025-01-

Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs		image2024-11-
Publish
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning		image2024-10-
Publish
SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models		image2024-06Github
Publish
Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models		image2024-02-
Publish
Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark		image2024-01Github

Datasets & Benchmarks

Visual-based data

TitleIntroductionDateCode

Planning with the Views		image2026-05Github
Publish
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?		image2026-02Github

EscherVerse: An Open World Benchmark and Dataset for Teleo-Spatial Intelligence with Physical-Dynamic and Intent-Driven Understanding		image2026-1Github

RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		image2025-12Github

Towards Cross-View Point Correspondence in Vision-Language Models		image2025-12Github
Publish
ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints		image2025-11-

Scaling Spatial Intelligence with Multimodal Foundation Models		image2025-11Github

SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition		image2025-11Github

Visual Spatial Tuning		image2025-11Github

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models		image2025-10Github

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence		image2025-10Github

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes		image2025-10-

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions		image2025-10Github

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs		image2025-09Github

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes		image2025-09Github

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture		image2025-09Github

VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning		image2025-08Github

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations		image2025-09Github
Publish
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models		image2025-08Github

11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis		image2025-08-
Publish
Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting		image2025-07Github

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models		image2025-07-

SpatialViz-Bench: An MLLM Benchmark for Spatial Visualization		image2025-07Github

Spatial Mental Modeling from Limited Views		image2025-06Github

SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks		image2025-06-
Publish
IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering		image2025-06Github
Publish
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes		image2025-06Github
Publish
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly		image2025-06Github

Can Vision Language Models Infer Human Gaze Direction? A Controlled Study		image2025-06Github

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence		image2025-06Github

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations		image2025-06Github

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models		image2025-06Github

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models		image2025-06-

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence		image2025-05Github
Publish
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		image2025-05Github

Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models		image2025-05Github

SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding		image2025-05Github

MIRAGE:A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence		image2025-05Github

Can Multimodal Large Language Models Understand Spatial Relations		image2025-05Github

Visuospatial Cognitive Assistant		image2025-05Github

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?		image2025-05Github

Vision language models have difficulty recognizing virtual objects		image2025-05-

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models		image2025-05Github

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames		image2025-05-
Publish
SITE: towards Spatial Intelligence Thorough Evaluation		image2025-05Github

CameraBench: Towards Understanding Camera Motions in Any Video		image2025-04Github

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs		image2025-04Github

From Flatland to Space:Teaching Vision-Language Models to Perceive and Reason in 3D		image2025-03Github

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLM		image2025-03-

Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space		image2025-03Github
Publish
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?		image2025-03Github
Publish
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models		image2025-03Github

Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models		image2025-03Github

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?		image2025-03Github
Publish
Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models		image2025-02Github

FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks		image2025-02-

iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs		image2025-02Github

Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics		image2025-02-
Publish
SAT: Spatial Aptitude Training for Multimodal Language Models		image2024-12Github
Publish
SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models		image2024-12Github
Publish
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark		image2024-12Github
StarPublish
Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces		image2024-12Github
Publish
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics		image2024-11Github
Publish
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models		image2024-11-
Publish
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos		image2024-11Github

Is ‘Right’ Right? Enhancing Object Orientation Understanding in Multimodal Language Models through Egocentric Instruction Tuning		image2024-10Github
Publish
ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models		image2024-10Github
Publish
DOES SPATIAL COGNITION EMERGE IN FRONTIER MODELS?		image2024-10-
Publish
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities		image2024-10Github

R2D3: Imparting Spatial Reasoning by Reconstructing 3D Scenes from 2D Images		image2024-10Github
Publish
Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models		image2024-09Github
Publish
Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?		image2024-09-

VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs		image2024-07Github
Publish
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models		image2024-06Github
Publish
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners		image2024-06Github
Publish
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models		image2024-06Github
Publish
GSR-Bench: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs		image2024-06-
Publish
Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning		image2024-05Github
Publish
Visually Descriptive Language Model for Vector Graphics Reasoning		image2024-04-
PublishStar
SQA3D: Situated Question Answering in 3D Scenes		image2022-10Github
PublishStar
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals		image2022-03Github
Publish
SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings		image2020-03Github

Text-based data

TitleIntroductionDateCode

Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning		image2024-12-

GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning		image2024-07-

Findings

TitleIntroductionDateCode

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks		image2025-10Github

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective		image2025-09Github

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study		image2025-08-

A Call for New Recipes to Enhance Spatial Reasoning in MLLMs		image2025-03Github

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas		image2025-03Github

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models		image2025-03Github

Applications

TitleIntroductionDateCode

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model		image2025-10Github

SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models		image2025-05-

InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning		image2025-05Github

EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks		image2025-03-

SOFAR: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation		image2025-02Github

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning		image2025-03Github

VL-Nav: Real-time Vision-Language Navigation with Spatial Reasoning		image2025-02-

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models		image2025-01Github
Publish
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection		image2024-12Github

EMMA-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning		image2024-12Github
Publish
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning		image2024-04Github
Publish
Improving Vision-and-Language Reasoning via Spatial Relations Modeling		image2023-11-
awesome-list
spatial-intelligence
spatial-reasoning
vision-language-models

Contributors

yyyybq

52 commits

Grady10086

5 commits

Zhoues

3 commits

jeasinema

2 commits

Similar repos

DishengLL/Awesome-Spatial-VLMs

5

vulab-AI/Awesome-Spatial-VLMs

[Awesome-Spatial-VLMs] This repository is the official, community-maintained resource for the…

471

SIBench/Awesome-Visual-Spatial-Reasoning

This is a project about visual spatial reasoning.

148

DirtyHarryLYL/LLM-in-Vision

Recent LLM-based CV and related works. Welcome to comment/contribute!

872

NOVAglow646/LLM-MLLM-paper-list

关于LLM和Multimodal LLM的paper list

65

The-Martyr/Awesome-Multimodal-Reasoning

Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs

103

CSU-JPG/Awesome-VLM-Reasoning

21

zhaochen0110/Awesome_Think_With_Images

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our…

1,509

mll-lab-nu/Awesome-Spatial-Intelligence-in-VLM

A paper list for spatial reasoning

786

83 commits

updated Aug 23, 2026

See the code

README

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

Methods

Visual-based methods

TitleIntroductionDateCode

Planning with the Views		image2026-05Github

RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		image2025-12Github

N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models		image2025-12Github

SpatialDreamer: Incentivizing Spatial Reasoning via Active Mental Imagery		image2025-12Github

Seeing through Imagination: Learning Scene Geometry via Implicit Spatial World Modeling		image2025-12Github

CVP: Central-Peripheral Vision-Inspired Multimodal Model for Spatial Reasoning		image2025-12-

S2-MLLM: Boosting Spatial Reasoning Capability of MLLMs for 3D Visual Grounding with Structural Guidance		image2025-12-

EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence		image2025-12-

Video4Spatial: Towards Visuospatial Intelligence with Context-Guided Video Generation		image2025-12-

Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning		image2025-11Github

G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning		image2025-11Github

Video Spatial Reasoning with Object-Centric 3D Rollout		image2025-11-

Abstract 3D Perception for Spatial Intelligence in Vision-Language Models		image2025-11-

SpaceMind: Camera-Guided Modality Fusion for Spatial Reasoning in Vision-Language Models		image2025-11-

Cambrian-S: Towards Spatial Supersensing in Video		image2025-11Github

Omni-View: Unlocking How Generation Facilitates Understanding in Unified 3D Model based on Multiview images		image2025-11Github

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards		image2025-11Github

TIGeR: Tool-Integrated Geometric Reasoning in Vision-Language Models for Robotics		image2025-10Github

Spatial-SSRL: Enhancing Spatial Understanding via Self-Supervised Reinforcement Learning		image2025-10Github

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation		image2025-10Github

Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views		image2025-10Github

Euclid’s Gift: Enhancing Spatial Perception and Reasoning in Vision-Language Models via Geometric Surrogate Tasks		image2025-10Github

SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models		image2025-10Github

SpaceVista: All-Scale Visual Spatial Reasoning from mm to km		image2025-10Github
Publish
SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models		image2025-09Github
Publish
See&Trek: Training-Free Spatial Prompting for Multimodal Large Language Model		image2025-09-

3D Aware Region Prompted Vision Language Model		image2025-09Github

UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding		image2025-08Github

SIFThinker: Spatially-Aware Image Focus for Visual Reasoning		image2025-08Github

Enhancing Spatial Reasoning through Visual and Textual Thinking		image2025-07-
Publish
MindJourney: Test-Time Scaling with World Models for Spatial Reasoning		image2025-07Github
Publish
Struct2D: A Perception-Guided Framework for Spatial Reasoning in Large Multimodal Models		image2025-06Github
Publish
Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs		image2025-06Github
Publish
SpatialLM: Training Large Language Models for Structured Indoor Modeling		image2025-06Github

Spatial Understanding from Videos: Structured Prompts Meet Simulation Data		image2025-06Github

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing		image2025-06Github

Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in Spaces		image2025-05Github
Publish
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		image2025-05Github
Publish
Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors		image2025-05Github
Publish
SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models		image2025-05Github
Publish
Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence		image2025-05Github

STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs		image2025-05Github

VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction		image2025-05Github

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding		image2025-05-
Publish
SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning		image2025-05Github
Publish
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation		image2025-04Github

Scaling and Beyond: Advancing Spatial Reasoning in MLLMs Requires New Recipe		image2025-04-

SpaceR: Reinforcing MLLMs in Video Spatial Reasoning		image2025-04Github

Embodied-R: Collaborative Framework for Activating Embodied Spatial Reasoning in Foundation Models via Reinforcement Learning		image2025-04Github
Publish
SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning		image2025-04Github
Publish
ROSS3D: Reconstructive Visual Instruction Tuning with 3D-Awareness		image2025-04Github
Publish
SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic Data		image2025-04-

Visual Agentic AI for Spatial Reasoning with a Dynamic API		image2025-02Github
Publish
Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding		image2025-01Github

SpatialCoT: Advancing Spatial Reasoning through Coordinate Alignment and Chain-of-Thought for Embodied Task Planning		image2025-01Github
Publish
LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Model		image2024-12Github

COARSE CORRESPONDENCES Boost Spatial-Temporal Reasoning in Multimodal Language Model		image2024-08Github
Star Publish
RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics		image2024-06GitHub
Star Publish
SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models		image2024-06Github
Star Publish
SpatialBot: Precise Spatial Understanding with Vision Language Models		image2024-06Github
Publish
Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs		image2024-04Github

SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors		image2024-03-
Publish
Can Transformers Capture Spatial Relations between Objects?		image2024-03Github
Star Publish
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities		image2024-01Github

Proximity QA: Unleashing the Power of Multi-Modal Large Language Models for Spatial Proximity Analysis		image2024-01Github

3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V		image2023-12-

Text-based methods

TitleIntroductionDateCode

Imagine while Reasoning in Space: Multimodal Visualization-of-Thought		image2025-01-

Dspy-based Neural-Symbolic Pipeline to Enhance Spatial Reasoning in LLMs		image2024-11-
Publish
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning		image2024-10-
Publish
SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models		image2024-06Github
Publish
Beyond Lines and Circles: Unveiling the Geometric Reasoning Gap in Large Language Models		image2024-02-
Publish
Advancing Spatial Reasoning in Large Language Models: An In-Depth Evaluation and Enhancement Using the StepGame Benchmark		image2024-01Github

Datasets & Benchmarks

Visual-based data

TitleIntroductionDateCode

Planning with the Views		image2026-05Github
Publish
Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?		image2026-02Github

EscherVerse: An Open World Benchmark and Dataset for Teleo-Spatial Intelligence with Physical-Dynamic and Intent-Driven Understanding		image2026-1Github

RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics		image2025-12Github

Towards Cross-View Point Correspondence in Vision-Language Models		image2025-12Github
Publish
ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints		image2025-11-

Scaling Spatial Intelligence with Multimodal Foundation Models		image2025-11Github

SpatialBench: Benchmarking Multimodal Large Language Models for Spatial Cognition		image2025-11Github

Visual Spatial Tuning		image2025-11Github

Spatial-DISE: A Unified Benchmark for Evaluating Spatial Reasoning in Vision-Language Models		image2025-10Github

DSI-Bench: A Benchmark for Dynamic Spatial Intelligence		image2025-10Github

Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes		image2025-10-

NavSpace: How Navigation Agents Follow Spatial Intelligence Instructions		image2025-10Github

SpinBench: Perspective and Rotation as a Lens on Spatial Reasoning in VLMs		image2025-09Github

Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes		image2025-09Github

Why Do MLLMs Struggle with Spatial Understanding? A Systematic Analysis from Data to Architecture		image2025-09Github

VisualTrans: A Benchmark for Real-World Visual Transformation Reasoning		image2025-08Github

SpatialVID: A Large-Scale Video Dataset with Spatial Annotations		image2025-09Github
Publish
VLM4D: Towards Spatiotemporal Awareness in Vision Language Models		image2025-08Github

11Plus-Bench: Demystifying Multimodal LLM Spatial Reasoning with Cognitive-Inspired Analysis		image2025-08-
Publish
Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting		image2025-07Github

Ascending the Infinite Ladder: Benchmarking Spatial Deformation Reasoning in Vision-Language Models		image2025-07-

SpatialViz-Bench: An MLLM Benchmark for Spatial Visualization		image2025-07Github

Spatial Mental Modeling from Limited Views		image2025-06Github

SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks		image2025-06-
Publish
IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering		image2025-06Github
Publish
From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes		image2025-06Github
Publish
PhyBlock: A Progressive Benchmark for Physical Understanding and Planning via 3D Block Assembly		image2025-06Github

Can Vision Language Models Infer Human Gaze Direction? A Controlled Study		image2025-06Github

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence		image2025-06Github

Unfolding Spatial Cognition: Evaluating Multimodal Models on Visual Simulations		image2025-06Github

OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models		image2025-06Github

InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models		image2025-06-

MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence		image2025-05Github
Publish
RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics		image2025-05Github

Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models		image2025-05Github

SpatialScore: Towards Unified Evaluation for Multimodal Spatial Understanding		image2025-05Github

MIRAGE:A Multi-modal Benchmark for Spatial Perception, Reasoning, and Intelligence		image2025-05Github

Can Multimodal Large Language Models Understand Spatial Relations		image2025-05Github

Visuospatial Cognitive Assistant		image2025-05Github

Are Multimodal Large Language Models Ready for Omnidirectional Spatial Reasoning?		image2025-05Github

Vision language models have difficulty recognizing virtual objects		image2025-05-

ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models		image2025-05Github

Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Frames		image2025-05-
Publish
SITE: towards Spatial Intelligence Thorough Evaluation		image2025-05Github

CameraBench: Towards Understanding Camera Motions in Any Video		image2025-04Github

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs		image2025-04Github

From Flatland to Space:Teaching Vision-Language Models to Perceive and Reason in 3D		image2025-03Github

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLM		image2025-03-

Open3DVQA: A Benchmark for Comprehensive Spatial Reasoning with Multimodal Large Language Model in Open Space		image2025-03Github
Publish
STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding?		image2025-03Github
Publish
CoSpace: Benchmarking Continuous Space Perception Ability for Vision-Language Models		image2025-03Github

Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models		image2025-03Github

LEGO-Puzzles: How Good Are MLLMs at Multi-Step Spatial Reasoning?		image2025-03Github
Publish
Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models		image2025-02Github

FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks		image2025-02-

iVISPAR — An Interactive Visual-Spatial Reasoning Benchmark for VLMs		image2025-02Github

Defining and Evaluating Visual Language Models' Basic Spatial Abilities: A Perspective from Psychometrics		image2025-02-
Publish
SAT: Spatial Aptitude Training for Multimodal Language Models		image2024-12Github
Publish
SPHERE: A Hierarchical Evaluation on Spatial Perception and Reasoning for Vision-Language Models		image2024-12Github
Publish
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark		image2024-12Github
StarPublish
Thinking in Space: How Multimodal Large Language Models See, Remember and Recall Spaces		image2024-12Github
Publish
RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics		image2024-11Github
Publish
An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models		image2024-11-
Publish
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos		image2024-11Github

Is ‘Right’ Right? Enhancing Object Orientation Understanding in Multimodal Language Models through Egocentric Instruction Tuning		image2024-10Github
Publish
ActiView: Evaluating Active Perception Ability for Multimodal Large Language Models		image2024-10Github
Publish
DOES SPATIAL COGNITION EMERGE IN FRONTIER MODELS?		image2024-10-
Publish
Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities		image2024-10Github

R2D3: Imparting Spatial Reasoning by Reconstructing 3D Scenes from 2D Images		image2024-10Github
Publish
Reasoning Paths with Reference Objects Elicit Quantitative Spatial Reasoning in Large Vision-Language Models		image2024-09Github
Publish
Can Vision Language Models Learn from Visual Demonstrations of Ambiguous Spatial Reasoning?		image2024-09-

VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for VLMs		image2024-07Github
Publish
EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models		image2024-06Github
Publish
TopViewRS: Vision-Language Models as Top-View Spatial Reasoners		image2024-06Github
Publish
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models		image2024-06Github
Publish
GSR-Bench: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs		image2024-06-
Publish
Reframing Spatial Reasoning Evaluation in Language Models: A Real-World Simulation Benchmark for Qualitative Reasoning		image2024-05Github
Publish
Visually Descriptive Language Model for Vector Graphics Reasoning		image2024-04-
PublishStar
SQA3D: Situated Question Answering in 3D Scenes		image2022-10Github
PublishStar
Things not Written in Text: Exploring Spatial Commonsense from Visual Signals		image2022-03Github
Publish
SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings		image2020-03Github

Text-based data

TitleIntroductionDateCode

Do Multimodal Language Models Really Understand Direction? A Benchmark for Compass Direction Reasoning		image2024-12-

GRASP: A Grid-Based Benchmark for Evaluating Commonsense Spatial Reasoning		image2024-07-

Findings

TitleIntroductionDateCode

Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks		image2025-10Github

How Far are VLMs from Visual Spatial Intelligence? A Benchmark-Driven Perspective		image2025-09Github

Has GPT-5 Achieved Spatial Intelligence? An Empirical Study		image2025-08-

A Call for New Recipes to Enhance Spatial Reasoning in MLLMs		image2025-03Github

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas		image2025-03Github

Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models		image2025-03Github

Applications

TitleIntroductionDateCode

Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model		image2025-10Github

SpatialPrompting: Keyframe-driven Zero-Shot Spatial Reasoning with Off-the-Shelf Multimodal Large Language Models		image2025-05-

InSpire: Vision-Language-Action Models with Intrinsic Spatial Reasoning		image2025-05Github

EmbodiedVSR: Dynamic Scene Graph-Guided Chain-of-Thought Reasoning for Visual Spatial Tasks		image2025-03-

SOFAR: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation		image2025-02Github

ReasonGrounder: LVLM-Guided Hierarchical Feature Splatting for Open-Vocabulary 3D Visual Grounding and Reasoning		image2025-03Github

VL-Nav: Real-time Vision-Language Navigation with Spatial Reasoning		image2025-02-

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Models		image2025-01Github
Publish
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection		image2024-12Github

EMMA-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning		image2024-12Github
Publish
Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning		image2024-04Github
Publish
Improving Vision-and-Language Reasoning via Spatial Relations Modeling		image2023-11-
awesome-list
spatial-intelligence
spatial-reasoning
vision-language-models

Similar repos

DishengLL/Awesome-Spatial-VLMs

5

vulab-AI/Awesome-Spatial-VLMs

[Awesome-Spatial-VLMs] This repository is the official, community-maintained resource for the…

471

SIBench/Awesome-Visual-Spatial-Reasoning

This is a project about visual spatial reasoning.

148

DirtyHarryLYL/LLM-in-Vision

Recent LLM-based CV and related works. Welcome to comment/contribute!

872

NOVAglow646/LLM-MLLM-paper-list

关于LLM和Multimodal LLM的paper list

65

The-Martyr/Awesome-Multimodal-Reasoning

Latest Advances on (RL based) Multimodal Reasoning and Generation in Multimodal LLMs

103

CSU-JPG/Awesome-VLM-Reasoning

21

zhaochen0110/Awesome_Think_With_Images

Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our…

1,509

Contributors

yyyybq

52 commits

Grady10086

5 commits

Zhoues

3 commits

jeasinema

2 commits