Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models

• URL: http://arxiv.org/abs/2608.26716v1
• Date: Thu, 27 Aug 2026 07:10:42 GMT
• Title: Beyond Atomic Layouts: Compositional Design Understanding with Vision-Language Models
• Abstract summary: We introduce a new task, compositional layout understanding, and present CoDe, a dataset of 20K real-world multi-layer annotated layouts.<n>To address these challenges, we propose MASON, a post-training paradigm that integrates multimodal alignment (MA) and structural perception (SP)<n> MASON enhances element interpretation by grounding metadata-defined elements to their visual counterparts, while SP models layer-aware inter-element relationships.
• Score: 50.81272588822916
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Layout understanding, or the interpretation of element organization, is essential for document analysis, user interface (UI) creation, and graphic design. While recent vision-language models (VLMs) excel at interpreting atomic layouts composed of independent elements, they struggle with compositional layouts that require reasoning over visually entangled elements within hierarchical multi-layer structures. In this paper, we introduce a new task, compositional layout understanding, and present CoDeLayout, a VQA dataset of ~20K real-world multi-layer layouts annotated with compositional element pairs and design intent. Through empirical analysis on CoDeLayout, we identify two key challenges for existing VLMs: semantic drift between textual metadata and visual content, and structural ambiguity in hierarchical inter-element relationships. To address these challenges, we propose MASON, a post-training paradigm that integrates multimodal alignment (MA) and structural perception (SP). MA enhances element interpretation by grounding metadata-defined elements to their visual counterparts, mitigating semantic drift, while SP models layer-aware inter-element spatial relationships to improve hierarchical understanding and reduce structural ambiguity. Experiments reveal substantial gaps in existing VLMs: even the strongest baseline, GPT-o3, achieves only 79.68% accuracy, whereas Qwen2.5-VL 7B with MASON reaches 91.66%. Notably, MASON surpasses full-data Direct Finetune using only 30% of the training data and scales better with additional data.

Related papers

• Dual-Pathway Geometry-Aware MLLM for Spatial Intelligence [63.11502936651325]
  We propose GAMSI, a dual-pathway Geometry-Aware MLLM for Spatial Intelligence.<n>It takes only RGB images as input while internalizing both forms of geometric prior within a unified autoregressive backbone.<n>GAMSI achieves state-of-the-art performance on seven spatial intelligence benchmarks.
  arXiv  Detail & Related papers  (2026-05-25T01:33:19Z)
• PARL: Position-Aware Relation Learning Network for Document Layout Analysis [23.497081928689525]
  We argue that effective layout analysis depends not on text-visual fusion, but on a deep understanding of documents' intrinsic visual structure.<n>We propose a novel OCR-free, vision-only framework that models layout through positional sensitivity and relational structure.<n>Experiments show that PARL (65M) is highly efficient, using roughly four times fewer parameters than large multimodal models.
  arXiv  Detail & Related papers  (2026-01-12T15:05:35Z)
• DisCo-Layout: Disentangling and Coordinating Semantic and Physical Refinement in a Multi-Agent Framework for 3D Indoor Layout Synthesis [76.7196710324494]
  3D indoor layout synthesis is crucial for creating virtual environments.<n>DisCo is a novel framework that disentangles and coordinates physical and semantic refinement.
  arXiv  Detail & Related papers  (2025-10-02T16:30:37Z)
• ReLayout: Integrating Relation Reasoning for Content-aware Layout Generation with Multi-modal Large Language Models [7.288330685534444]
  We introduce Re, a novel method that leverages relation-CoT to generate more reasonable and coherent layouts.<n>Specifically, we enhance layout annotations by introducing explicit relation definitions, such as region, salient, and margin between elements.<n>We also introduce a layout prototype sampler, which defines layout prototype features across three dimensions and quantifies distinct layout styles.
  arXiv  Detail & Related papers  (2025-07-08T01:13:43Z)
• Progressive Multi-granular Alignments for Grounded Reasoning in Large Vision-Language Models [19.054780489639793]
  This paper introduces Progressive multi-granular Vision-Language alignments (PromViL)<n>Our approach constructs a hierarchical structure of multi-modal alignments, ranging from simple to complex concepts.<n>By progressively aligning textual descriptions with corresponding visual regions, our model learns to leverage contextual information from lower levels to inform higher-level reasoning.
  arXiv  Detail & Related papers  (2024-12-11T06:21:33Z)
• GLDesigner: Leveraging Multi-Modal LLMs as Designer for Enhanced Aesthetic Text Glyph Layouts [53.568057283934714]
  We propose a Vision-Language Model (VLM)-based framework that generates content-aware text logo layouts.<n>We introduce two model techniques that reduce the computational cost for processing multiple glyph images simultaneously.<n>To support instruction tuning of our model, we construct two extensive text logo datasets that are five times larger than existing public datasets.
  arXiv  Detail & Related papers  (2024-11-18T10:04:10Z)
• ComAlign: Compositional Alignment in Vision-Language Models [2.3250871476216814]
  We introduce Compositional Alignment (ComAlign) to discover more exact correspondence of text and image components. Our methodology emphasizes that the compositional structure extracted from the text modality must also be retained in the image modality. We train a lightweight network lying on top of existing visual and language encoders using a small dataset.
  arXiv  Detail & Related papers  (2024-09-12T16:46:41Z)
• Enhancing Visually-Rich Document Understanding via Layout Structure Modeling [91.07963806829237]
  We propose GraphLM, a novel document understanding model that injects layout knowledge into the model. We evaluate our model on various benchmarks, including FUNSD, XFUND and CORD, and achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2023-08-15T13:53:52Z)
• Support-set based Multi-modal Representation Enhancement for Video Captioning [121.70886789958799]
  We propose a Support-set based Multi-modal Representation Enhancement (SMRE) model to mine rich information in a semantic subspace shared between samples. Specifically, we propose a Support-set Construction (SC) module to construct a support-set to learn underlying connections between samples and obtain semantic-related visual elements. During this process, we design a Semantic Space Transformation (SST) module to constrain relative distance and administrate multi-modal interactions in a self-supervised way.
  arXiv  Detail & Related papers  (2022-05-19T03:40:29Z)
• MGA-VQA: Multi-Granularity Alignment for Visual Question Answering [75.55108621064726]
  Learning to answer visual questions is a challenging task since the multi-modal inputs are within two feature spaces. We propose Multi-Granularity Alignment architecture for Visual Question Answering task (MGA-VQA) Our model splits alignment into different levels to achieve learning better correlations without needing additional data and annotations.
  arXiv  Detail & Related papers  (2022-01-25T22:30:54Z)
• VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations [40.721146438291335]
  We propose a unified framework VSR for document layout analysis, combining vision, semantics and relations. On three popular benchmarks, VSR outperforms previous models by large margins.
  arXiv  Detail & Related papers  (2021-05-13T12:20:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.