# SPARTUN3D: Situated Spatial Understanding of 3D World in Large Language Models

arXiv: https://arxiv.org/abs/2410.03878 · HTML: https://mlsanity.com/paper/2410.03878/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 64 references that are in the map.
- First posted on arXiv 4 Oct 2024.

## Builds on (most cited first, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments](https://mlsanity.com/paper/1711.07280/) (2017)
- [CLIPort: What and Where Pathways for Robotic Manipulation](https://mlsanity.com/paper/2109.12098/) (2021)
- [SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities](https://mlsanity.com/paper/2305.11000/) (2023)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [An Embodied Generalist Agent in 3D World](https://mlsanity.com/paper/2311.12871/) (2023)
- [ScanQA: 3D Question Answering for Spatial Scene Understanding](https://mlsanity.com/paper/2112.10482/) (2021)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [SQA3D: Situated Question Answering in 3D Scenes](https://mlsanity.com/paper/2210.07474/) (2022)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models](https://mlsanity.com/paper/2305.16986/) (2023)
- [Scan2Cap: Context-aware Dense Captioning in RGB-D Scans](https://mlsanity.com/paper/2012.02206/) (2020)
- [LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning](https://mlsanity.com/paper/2311.18651/) (2023)
- [3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment](https://mlsanity.com/paper/2308.04352/) (2023)
- [Text2Shape: Generating Shapes from Natural Language by Learning Joint Embeddings](https://mlsanity.com/paper/1803.08495/) (2018)

## Built on by (most cited first, 27 of 27)

- [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024)
- [Spatial Reasoning with Vision-Language Models in Ego-Centric Multi-View Scenes](https://mlsanity.com/paper/2509.06266/) (2025)
- [On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection](https://mlsanity.com/paper/2410.23623/) (2024)
- [Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector](https://mlsanity.com/paper/2503.20188/) (2025)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [Spatial Understanding from Videos: Structured Prompts Meet Simulation Data](https://mlsanity.com/paper/2506.03642/) (2025)
- [SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence](https://mlsanity.com/paper/2506.07966/) (2025)
- [3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting](https://mlsanity.com/paper/2412.01583/) (2024)
- [When and How Much to Imagine: Adaptive Test-Time Scaling with World Models for Visual Spatial Reasoning](https://mlsanity.com/paper/2602.08236/) (2026)
- [GaussianVLM: Scene-centric 3D Vision-Language Models using Language-aligned Gaussian Splats for Embodied Reasoning and Beyond](https://mlsanity.com/paper/2507.00886/) (2025)
- [Do 3D Large Language Models Really Understand 3D Spatial Relationships?](https://mlsanity.com/paper/2603.23523/) (2026)
- [HIS-GPT: Towards 3D Human-In-Scene Multimodal Understanding](https://mlsanity.com/paper/2503.12955/) (2025)
- [MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregation](https://mlsanity.com/paper/2506.17113/) (2025)
- [Hypo3D: Exploring Hypothetical Reasoning in 3D](https://mlsanity.com/paper/2502.00954/) (2025)
- [SAM-Guided Masked Token Prediction for 3D Scene Understanding](https://mlsanity.com/paper/2410.12158/) (2024)
- [MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents](https://mlsanity.com/paper/2505.20148/) (2025)
- [Vision-and-Language Navigation with Analogical Textual Descriptions in LLMs](https://mlsanity.com/paper/2509.25139/) (2025)
- [Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model](https://mlsanity.com/paper/2510.11509/) (2025)
- [What if? Emulative Simulation with World Models for Situated Reasoning](https://mlsanity.com/paper/2603.06445/) (2026)
- [Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?](https://mlsanity.com/paper/2605.30557/) (2026)
- [FoR-SALE: Frame of Reference-guided Spatial Adjustment in LLM-based Diffusion Editing](https://mlsanity.com/paper/2509.23452/) (2025)
- [Imagine in Space: Exploring the Frontier of Spatial Intelligence and Reasoning Efficiency in Vision Language Models](https://mlsanity.com/paper/2511.13782/) (2025)
- [Error-Driven Scene Editing for 3D Grounding in Large Language Models](https://mlsanity.com/paper/2511.14086/) (2025)
- [SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video](https://mlsanity.com/paper/2607.01784/) (2026)
- [HMR3D: Hierarchical Multimodal Representation for 3D Scene Understanding with Large Vision-Language Model](https://mlsanity.com/paper/2511.22961/) (2025)
- [Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems](https://mlsanity.com/paper/2601.14091/) (2026)
- [EgoAlign: Situated 3D Understanding without Situation Descriptions](https://mlsanity.com/paper/2610.16176/) (2026)

## Abstract (arXiv)

Integrating the 3D world into large language models (3D-based LLMs) has been a promising research direction for 3D scene understanding. However, current 3D-based LLMs fall short in situated understanding due to two key limitations: 1) existing 3D datasets are constructed from a global perspective of the 3D scenes and lack situated context. 2) the architectures of existing 3D-based LLMs lack explicit alignment between the spatial representations of 3D scenes and natural language, limiting their performance in tasks requiring precise spatial reasoning. We address these issues by introducing a scalable situated 3D dataset, named Spartun3D, that incorporates various situated spatial reasoning tasks. Furthermore, we propose Spartun3D-LLM, built on an existing 3D-based LLM but integrated with a novel situated spatial alignment module, aiming to enhance the alignment between 3D visual representations and their corresponding textual descriptions. Experimental results demonstrate that both our proposed dataset and alignment module significantly enhance the situated spatial understanding of 3D-based LLMs.