# SpatialLM: Training Large Language Models for Structured Indoor Modeling

arXiv: https://arxiv.org/abs/2506.07491 · HTML: https://mlsanity.com/paper/2506.07491/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 69 references that are in the map.
- First posted on arXiv 9 Jun 2025.

## Builds on (most cited first, 30 of 62)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes](https://mlsanity.com/paper/2308.11417/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding](https://mlsanity.com/paper/2011.02523/) (2020)
- [Point Transformer V3: Simpler, Faster, Stronger](https://mlsanity.com/paper/2312.10035/) (2023)
- [ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data](https://mlsanity.com/paper/2111.08897/) (2021)
- [ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language](https://mlsanity.com/paper/1912.08830/) (2019)
- [Point Transformer V2: Grouped Vector Attention and Partition-based Pooling](https://mlsanity.com/paper/2210.05666/) (2022)
- [ProcTHOR: Large-Scale Embodied AI Using Procedural Generation](https://mlsanity.com/paper/2206.06994/) (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)
- [Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Models](https://mlsanity.com/paper/2402.07865/) (2024)

## Built on by (most cited first, 30 of 65)

- [N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models](https://mlsanity.com/paper/2512.16561/) (2025)
- [LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans](https://mlsanity.com/paper/2507.02861/) (2025)
- [DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning](https://mlsanity.com/paper/2512.12799/) (2025)
- [SPATIALGEN: Layout-guided 3D Indoor Scene Generation](https://mlsanity.com/paper/2509.14981/) (2025)
- [Towards Spatial Trace with Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2512.13660/) (2025)
- [SpatialTree: How Spatial Abilities Branch Out in MLLMs](https://mlsanity.com/paper/2512.20617/) (2025)
- [OmniInsert: Mask-Free Video Insertion of Any Reference via Diffusion Transformer Models](https://mlsanity.com/paper/2509.17627/) (2025)
- [SpatialNav: Leveraging Spatial Scene Graphs for Zero-Shot Vision-and-Language Navigation](https://mlsanity.com/paper/2601.06806/) (2026)
- [ArtLLM: Generating Articulated Assets via 3D LLM](https://mlsanity.com/paper/2603.01142/) (2026)
- [SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks](https://mlsanity.com/paper/2506.14512/) (2025)
- [Thinking with Spatial Code for Physical-World Video Reasoning](https://mlsanity.com/paper/2603.05591/) (2026)
- [Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D](https://mlsanity.com/paper/2604.05212/) (2026)
- [Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence](https://mlsanity.com/paper/2603.07660/) (2026)
- [Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting](https://mlsanity.com/paper/2509.24421/) (2025)
- [LottieGPT: Tokenizing Vector Animation for Autoregressive Generation](https://mlsanity.com/paper/2604.11792/) (2026)
- [From 2D to 3D Cognition: A Brief Survey of General World Models](https://mlsanity.com/paper/2506.20134/) (2025)
- [OVSeg3R: Learn Open-vocabulary Instance Segmentation from 2D via 3D Reconstruction](https://mlsanity.com/paper/2509.23541/) (2025)
- [How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?](https://mlsanity.com/paper/2511.05449/) (2025)
- [Zoo3D: Zero-Shot 3D Object Detection at Scene Level](https://mlsanity.com/paper/2511.20253/) (2025)
- [OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics](https://mlsanity.com/paper/2512.08625/) (2025)
- [Towards Spatial Supersensing in the Wild](https://mlsanity.com/paper/2607.13681/) (2026)
- [HiSpatial: Taming Hierarchical 3D Spatial Understanding in Vision-Language Models](https://mlsanity.com/paper/2603.25411/) (2026)
- [Repurposing 3D Generative Model for Autoregressive Layout Generation](https://mlsanity.com/paper/2604.16299/) (2026)
- [Arcadia: Toward a Full-Lifecycle Framework for Embodied Lifelong Learning](https://mlsanity.com/paper/2512.00076/) (2025)
- [OnlineSI: Taming Large Language Model for Online 3D Understanding and Grounding](https://mlsanity.com/paper/2601.16538/) (2026)
- [SoPE: Spherical Coordinate-Based Positional Embedding for Enhancing Spatial Perception of 3D LVLMs](https://mlsanity.com/paper/2602.22716/) (2026)
- [Few-Shot Incremental 3D Object Detection in Dynamic Indoor Environments](https://mlsanity.com/paper/2604.07997/) (2026)
- [SpatialGrammar: A Domain-Specific Language for LLM-Based 3D Indoor Scene Generation](https://mlsanity.com/paper/2604.27555/) (2026)
- [ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models](https://mlsanity.com/paper/2605.20837/) (2026)
- [NaLA: A 3D Native LLM Layout Agent for High-quality 3D Scene Generation](https://mlsanity.com/paper/2606.29395/) (2026)

## Abstract (arXiv)

SpatialLM is a large language model designed to process 3D point cloud data and generate structured 3D scene understanding outputs. These outputs include architectural elements like walls, doors, windows, and oriented object boxes with their semantic categories. Unlike previous methods which exploit task-specific network designs, our model adheres to the standard multimodal LLM architecture and is fine-tuned directly from open-source LLMs. To train SpatialLM, we collect a large-scale, high-quality synthetic dataset consisting of the point clouds of 12,328 indoor scenes (54,778 rooms) with ground-truth 3D annotations, and conduct a careful study on various modeling and training decisions. On public benchmarks, our model gives state-of-the-art performance in layout estimation and competitive results in 3D object detection. With that, we show a feasible path for enhancing the spatial understanding capabilities of modern LLMs for applications in augmented reality, embodied robotics, and more.