# Visual Structures Helps Visual Reasoning: Addressing the Binding Problem in VLMs

arXiv: https://arxiv.org/abs/2506.22146 · HTML: https://mlsanity.com/paper/2506.22146/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 46 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## 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, 20 of 20)

- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Large Language Models Cannot Self-Correct Reasoning Yet](https://mlsanity.com/paper/2310.01798/) (2023)
- [Towards Reasoning in Large Language Models: A Survey](https://mlsanity.com/paper/2212.10403/) (2022)
- [Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models](https://mlsanity.com/paper/2406.09403/) (2024)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [On the Binding Problem in Artificial Neural Networks](https://mlsanity.com/paper/2012.05208/) (2020)
- [Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search](https://mlsanity.com/paper/2412.18319/) (2024)
- [PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding](https://mlsanity.com/paper/2501.16411/) (2025)
- [Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions](https://mlsanity.com/paper/2411.14405/) (2024)
- [Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark](https://mlsanity.com/paper/2501.05444/) (2025)
- [Can ChatGPT Forecast Stock Price Movements? Return Predictability and Large Language Models](https://mlsanity.com/paper/2304.07619/) (2023)
- [OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles](https://mlsanity.com/paper/2503.17352/) (2025)
- [Does Spatial Cognition Emerge in Frontier Models?](https://mlsanity.com/paper/2410.06468/) (2024)
- [An Empirical Analysis on Spatial Reasoning Capabilities of Large Multimodal Models](https://mlsanity.com/paper/2411.06048/) (2024)
- [Financial Statement Analysis with Large Language Models](https://mlsanity.com/paper/2407.17866/) (2024)
- [How Far Are We from Intelligent Visual Deductive Reasoning?](https://mlsanity.com/paper/2403.04732/) (2024)
- [LVLM-COUNT: Enhancing the Counting Ability of Large Vision-Language Models](https://mlsanity.com/paper/2412.00686/) (2024)
- [Grid Cell Path Integration For Movement-Based Visual Object Recognition](https://mlsanity.com/paper/2102.09076/) (2021)

## Built on by (most cited first, 15 of 15)

- [Large Language Model Reasoning Failures](https://mlsanity.com/paper/2602.06176/) (2026)
- [Toward Cognitive Supersensing in Multimodal Large Language Model](https://mlsanity.com/paper/2602.01541/) (2026)
- [Uncovering Grounding IDs: How External Cues Shape Multimodal Binding](https://mlsanity.com/paper/2509.24072/) (2025)
- [Understanding Counting Mechanisms in Large Language and Vision-Language Models](https://mlsanity.com/paper/2511.17699/) (2025)
- [VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?](https://mlsanity.com/paper/2603.07888/) (2026)
- [MultiView-Bench: A Diagnostic Benchmark for World-Centric Multi-View Integration in VLMs](https://mlsanity.com/paper/2607.08970/) (2026)
- [Visual Prompt Discovery via Semantic Exploration](https://mlsanity.com/paper/2603.16250/) (2026)
- [SketchVLM: Vision language models can annotate images to explain thoughts and guide users](https://mlsanity.com/paper/2604.22875/) (2026)
- [When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks](https://mlsanity.com/paper/2604.27272/) (2026)
- [PGT: Procedurally Generated Tasks for improving visual grounding in MLLMs](https://mlsanity.com/paper/2605.23883/) (2026)
- [Binding Visual Features Point by Point](https://mlsanity.com/paper/2605.25427/) (2026)
- [ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams](https://mlsanity.com/paper/2607.24707/) (2026)
- [Improving Spatial-Temporal Reasoning in Video-Language Models with Structured Video Prompting](https://mlsanity.com/paper/2608.28666/) (2026)
- [BindCLIP: One Balanced Coupling For Compositional Vision Language Scoring](https://mlsanity.com/paper/2609.23717/) (2026)
- [Why VLMs Miss Small Objects, and When Zooming In Is Safe](https://mlsanity.com/paper/2610.09313/) (2026)

## Abstract (arXiv)

Despite progress in Large Vision-Language Models (LVLMs), their capacity for visual reasoning is often limited by the binding problem: the failure to reliably associate perceptual features with their correct visual referents. This limitation underlies persistent errors in tasks such as counting, visual search, scene description, and spatial relationship understanding. A key factor is that current LVLMs process visual features largely in parallel, lacking mechanisms for spatially grounded, serial attention. This paper introduces Visual Input Structure for Enhanced Reasoning (VISER), a simple, effective method that augments visual inputs with low-level spatial structures and pairs them with a textual prompt that encourages sequential, spatially-aware parsing. We empirically demonstrate substantial performance improvements across core visual reasoning tasks, using only a single-query inference. Specifically, VISER improves GPT-4o performance on visual search, counting, and spatial relationship tasks by 25.0%, 26.8%, and 9.5%, respectively, and reduces edit distance error in scene description by 0.32 on 2D datasets. Furthermore, we find that the visual modification is essential for these gains; purely textual strategies, including Chain-of-Thought prompting, are insufficient and can even degrade performance. VISER underscores the importance of visual input design over purely linguistically based reasoning strategies and suggests that visual structuring is a powerful and general approach for enhancing compositional and spatial reasoning in LVLMs.