# Towards Grounded Visual Spatial Reasoning in Multi-Modal Vision Language Models

arXiv: https://arxiv.org/abs/2308.09778 · HTML: https://mlsanity.com/paper/2308.09778/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 31 of its 40 references that are in the map.
- First posted on arXiv 18 Aug 2023.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- 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 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning](https://mlsanity.com/paper/1612.06890/) (2016)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding](https://mlsanity.com/paper/2104.12763/) (2021)
- [FLAVA: A Foundational Language And Vision Alignment Model](https://mlsanity.com/paper/2112.04482/) (2021)
- [SimVLM: Simple Visual Language Model Pretraining with Weak Supervision](https://mlsanity.com/paper/2108.10904/) (2021)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [A Corpus for Reasoning About Natural Language Grounded in Photographs](https://mlsanity.com/paper/1811.00491/) (2018)
- [Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers](https://mlsanity.com/paper/2103.15679/) (2021)
- [Visual Spatial Reasoning](https://mlsanity.com/paper/2205.00363/) (2022)
- [Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts](https://mlsanity.com/paper/2111.08276/) (2021)
- [ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension](https://mlsanity.com/paper/2204.05991/) (2022)
- [Probing Image-Language Transformers for Verb Understanding](https://mlsanity.com/paper/2106.09141/) (2021)
- [Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers](https://mlsanity.com/paper/2109.04448/) (2021)
- [Towards General Purpose Vision Systems](https://mlsanity.com/paper/2104.00743/) (2021)
- [Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs](https://mlsanity.com/paper/2305.06343/) (2023)

## Built on by (most cited first, 18 of 18)

- [RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics](https://mlsanity.com/paper/2411.16537/) (2024)
- [OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models](https://mlsanity.com/paper/2506.03135/) (2025)
- [Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities](https://mlsanity.com/paper/2410.17385/) (2024)
- [GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs](https://mlsanity.com/paper/2406.13246/) (2024)
- [iVISPAR -- An Interactive Visual-Spatial Reasoning Benchmark for VLMs](https://mlsanity.com/paper/2502.03214/) (2025)
- [Logic-RAG: Augmenting Large Multimodal Models with Visual-Spatial Knowledge for Road Scene Understanding](https://mlsanity.com/paper/2503.12663/) (2025)
- [Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap](https://mlsanity.com/paper/2604.16256/) (2026)
- [I Know About "Up"! Enhancing Spatial Reasoning in Visual Language Models Through 3D Reconstruction](https://mlsanity.com/paper/2407.14133/) (2024)
- [BOP-ASK: Object-Interaction Reasoning for Vision-Language Models](https://mlsanity.com/paper/2511.16857/) (2025)
- [World2VLM: Distilling World Model Imagination into VLMs for Dynamic Spatial Reasoning](https://mlsanity.com/paper/2604.26934/) (2026)
- [Q-GroundCAM: Quantifying Grounding in Vision Language Models via GradCAM](https://mlsanity.com/paper/2404.19128/) (2024)
- [Structured Spatial Reasoning with Open Vocabulary Object Detectors](https://mlsanity.com/paper/2410.07394/) (2024)
- [Synergistic Dual Spatial-aware Generation of Image-to-Text and Text-to-Image](https://mlsanity.com/paper/2410.15312/) (2024)
- [Compositional Image-Text Matching and Retrieval by Grounding Entities](https://mlsanity.com/paper/2505.02278/) (2025)
- [Hierarchical Contextual Grounding LVLM: Enhancing Fine-Grained Visual-Language Understanding with Robust Grounding](https://mlsanity.com/paper/2508.16974/) (2025)
- [Spatial-ViLT: Enhancing Visual Spatial Reasoning through Multi-Task Learning](https://mlsanity.com/paper/2510.03441/) (2025)
- [Reinforcing Dual-Path Reasoning in Spatial Vision Language Models](https://mlsanity.com/paper/2606.17539/) (2026)
- [Multi-Level LVLM Guidance for Untrimmed Video Action Recognition](https://mlsanity.com/paper/2508.17442/) (2025)

## Abstract (arXiv)

Large vision-and-language models (VLMs) trained to match images with text on large-scale datasets of image-text pairs have shown impressive generalization ability on several vision and language tasks. Several recent works, however, showed that these models lack fine-grained understanding, such as the ability to count and recognize verbs, attributes, or relationships. The focus of this work is to study the understanding of spatial relations. This has been tackled previously using image-text matching (e.g., Visual Spatial Reasoning benchmark) or visual question answering (e.g., GQA or VQAv2), both showing poor performance and a large gap compared to human performance. In this work, we show qualitatively (using explainability tools) and quantitatively (using object detectors) that the poor object localization "grounding" ability of the models is a contributing factor to the poor image-text matching performance. We propose an alternative fine-grained, compositional approach for recognizing and ranking spatial clauses that combines the evidence from grounding noun phrases corresponding to objects and their locations to compute the final rank of the spatial clause. We demonstrate the approach on representative VLMs (such as LXMERT, GPV, and MDETR) and compare and highlight their abilities to reason about spatial relationships.