Mario: Multimodal Graph Reasoning with Large Language Models

• URL: http://arxiv.org/abs/2603.05181v1
• Date: Thu, 05 Mar 2026 13:49:41 GMT
• Title: Mario: Multimodal Graph Reasoning with Large Language Models
• Authors: Yuanfu Sun, Kang Li, Pengkang Guo, Jiajin Liu, Qiaoyu Tan,
• Abstract summary: Mario is a graph-conditioned VLM that refines textual and visual features through fine-grained cross-modal contrastive learning.<n>Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction.
• Score: 10.232888977666418
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario.

Related papers

• Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach [42.970648490410504]
  Multimodal Graph Foundation Models (MGFMs) allow for leveraging the rich multimodal information in Multimodal-Attributed Graphs (MAGs)<n>We propose PLANET, a novel framework employing a Divide-and-Conquer strategy to decouple modality interaction and alignment across distinct granularities.<n>We show that PLANET significantly outperforms state-of-the-art baselines across diverse graph-centric and multimodal generative tasks.
  arXiv  Detail & Related papers  (2026-02-04T01:05:12Z)
• Language-Guided Graph Representation Learning for Video Summarization [96.2763459348758]
  We propose a novel Language-guided Graph Representation Learning Network (LGRLN) for video summarization.<n>Specifically, we introduce a video graph generator that converts video frames into a structured graph to preserve temporal order and contextual dependencies.<n>Our method outperforms existing approaches across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-11-14T04:35:48Z)
• Graph4MM: Weaving Multimodal Learning with Structural Information [52.16646463590474]
  Graphs provide powerful structural information for modeling intra- and inter-modal relationships.<n>Previous works fail to distinguish multi-hop neighbors and treat the graph as a standalone modality.<n>We propose Graph4MM, a graph-based multimodal learning framework.
  arXiv  Detail & Related papers  (2025-10-19T20:13:03Z)
• MGCR-Net:Multimodal Graph-Conditioned Vision-Language Reconstruction Network for Remote Sensing Change Detection [55.702662643521265]
  We propose the multimodal graph-conditioned vision-language reconstruction network (MGCR-Net) to explore the semantic interaction capabilities of multimodal data.<n> Experimental results on four public datasets demonstrate that MGCR achieves superior performance compared to mainstream CD methods.
  arXiv  Detail & Related papers  (2025-08-03T02:50:08Z)
• Graph-MLLM: Harnessing Multimodal Large Language Models for Multimodal Graph Learning [23.089644598166885]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in representing and understanding diverse modalities.<n>Integrating multimodality with structured graph information (i.e., multimodal graphs, MMGs) is essential for real-world applications such as social networks, healthcare, and recommendation systems.<n>Existing MMG learning methods fall into three paradigms based on how they leverage MLLMs.
  arXiv  Detail & Related papers  (2025-06-12T01:44:46Z)
• MLaGA: Multimodal Large Language and Graph Assistant [9.985787670804823]
  Large Language Models (LLMs) have demonstrated substantial efficacy in advancing graph-structured data analysis.<n>We introduce the Multimodal Large Language and Graph Assistant (MLaGA), an innovative model that adeptly extends LLM capabilities to facilitate reasoning over complex graph structures and multimodal attributes.
  arXiv  Detail & Related papers  (2025-06-03T07:52:00Z)
• LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models [87.68057302738457]
  Text-Attributed Graphs (TAGs) are ubiquitous in real-world scenarios.<n>Despite large efforts to integrate Large Language Models (LLMs) and Graph Neural Networks (GNNs) for TAGs, existing approaches suffer from decoupled architectures.<n>We propose PromptGFM, a versatile GFM for TAGs grounded in graph vocabulary learning.
  arXiv  Detail & Related papers  (2025-03-05T09:45:22Z)
• UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs [34.48393396390799]
  We propose a novel cross-domain graph foundation model that enables general representation learning on multimodal graphs.<n>UniGraph2 employs modality-specific encoders alongside a graph neural network (GNN) to learn a unified low-dimensional embedding space.<n>We show that UniGraph2 significantly outperforms state-of-the-art models in tasks such as representation learning, transfer learning, and multimodal generative tasks.
  arXiv  Detail & Related papers  (2025-02-02T14:04:53Z)
• Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision? [62.12375949429938]
  We propose a multi-modal prompt learning paradigm to adapt pre-trained Graph Neural Networks to downstream tasks and data.<n>Our new paradigm embeds the graphs directly in the same space as the Large Language Models (LLMs) by learning both graph prompts and text prompts simultaneously.<n>We build the first CLIP-style zero-shot classification prototype that can generalize GNNs to unseen classes with extremely weak text supervision.
  arXiv  Detail & Related papers  (2024-12-11T08:03:35Z)
• Multi-Modal Video Dialog State Tracking in the Wild [10.453212911612866]
  MST-MIXER is a novel video dialog model operating over a generic multi-modal state tracking scheme. It predicts the missing underlying structure of the selected constituents of each input modality using a novel multi-modal graph structure learning method. It achieves new state-of-the-art results on five challenging benchmarks.
  arXiv  Detail & Related papers  (2024-07-02T12:34:17Z)
• mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections [104.14624185375897]
  mPLUG is a new vision-language foundation model for both cross-modal understanding and generation. It achieves state-of-the-art results on a wide range of vision-language downstream tasks, such as image captioning, image-text retrieval, visual grounding and visual question answering.
  arXiv  Detail & Related papers  (2022-05-24T11:52:06Z)

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.