# Stitch and Tell: A Structured Multimodal Data Augmentation Method for Spatial Understanding

arXiv: https://arxiv.org/abs/2512.06769 · HTML: https://mlsanity.com/paper/2512.06769/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 32 of its 44 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 30 of 32)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [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)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs](https://mlsanity.com/paper/2406.16860/) (2024)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces](https://mlsanity.com/paper/2412.14171/) (2024)
- [DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models](https://mlsanity.com/paper/2402.12289/) (2024)
- [V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs](https://mlsanity.com/paper/2312.14135/) (2023)
- [SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models](https://mlsanity.com/paper/2406.01584/) (2024)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [MLLMs Know Where to Look: Training-free Perception of Small Visual Details with Multimodal LLMs](https://mlsanity.com/paper/2502.17422/) (2025)
- [Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoning](https://mlsanity.com/paper/2403.11401/) (2024)
- [Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models](https://mlsanity.com/paper/2408.15556/) (2024)
- [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024)
- [Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models](https://mlsanity.com/paper/2406.14852/) (2024)
- [Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation](https://mlsanity.com/paper/2305.16289/) (2023)
- [MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs](https://mlsanity.com/paper/2503.13111/) (2025)
- [Evaluating Spatial Understanding of Large Language Models](https://mlsanity.com/paper/2310.14540/) (2023)
- [MixGen: A New Multi-Modal Data Augmentation](https://mlsanity.com/paper/2206.08358/) (2022)
- [Large Language Models are Visual Reasoning Coordinators](https://mlsanity.com/paper/2310.15166/) (2023)
- [Learning to Localize Objects Improves Spatial Reasoning in Visual-LLMs](https://mlsanity.com/paper/2404.07449/) (2024)
- [Data Augmentation techniques in time series domain: A survey and taxonomy](https://mlsanity.com/paper/2206.13508/) (2022)
- [A Survey on Data Synthesis and Augmentation for Large Language Models](https://mlsanity.com/paper/2410.12896/) (2024)
- [StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data](https://mlsanity.com/paper/2308.10253/) (2023)
- [Multimodal Large Language Models for Image, Text, and Speech Data Augmentation: A Survey](https://mlsanity.com/paper/2501.18648/) (2025)

## Abstract (arXiv)

Existing vision-language models often suffer from spatial hallucinations, i.e., generating incorrect descriptions about the relative positions of objects in an image. We argue that this problem mainly stems from the asymmetric properties between images and text. To enrich the spatial understanding ability of vision-language models, we propose a simple, annotation-free, plug-and-play method named Stitch and Tell (abbreviated as SiTe), which injects structured spatial supervision into data. It constructs stitched image-text pairs by stitching images along a spatial axis and generating spatially-aware captions or question answer pairs based on the layout of stitched image, without relying on costly advanced models or human involvement. We evaluate SiTe across three architectures including LLaVA-v1.5-7B, LLaVA-Qwen2-1.5B and HALVA-7B, two training datasets, and eight benchmarks. Experiments show that SiTe improves spatial understanding tasks such as MMEPosition (+5.50%) and Spatial-MM (+4.19%), while maintaining or improving performance on general vision-language benchmarks including COCO-QA (+1.02%) and MMBench (+4.76%). Our findings suggest that explicitly injecting spatially-aware structure into training data offers an effective way to mitigate spatial hallucinations and improve spatial understanding, while preserving general vision-language capabilities.