Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images

• URL: http://arxiv.org/abs/2510.21828v1
• Date: Wed, 22 Oct 2025 02:23:40 GMT
• Title: Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images
• Authors: Yichi Zhang, Zhuo Chen, Lingbing Guo, Lei Liang, Wen Zhang, Huajun Chen,
• Abstract summary: This paper bridges the dual gaps in large-scale high-quality data and capability enhancement methodologies.<n>We introduce STAR-64K, a dataset comprising 64K high-quality multi-modal instruction samples, and conduct experiments across 5 open-source MLLMs.
• Score: 58.553448128258566
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Understanding and reasoning with abstractive information from the visual modality presents significant challenges for current multi-modal large language models (MLLMs). Among the various forms of abstractive information, Multi-Modal Relational Knowledge (MMRK), which represents abstract relational structures between multi-modal entities using node-edge formats, remains largely under-explored. In particular, STructured and Abstractive Reasoning (STAR) on such data has received little attention from the research community. To bridge the dual gaps in large-scale high-quality data and capability enhancement methodologies, this paper makes the following key contributions: (i). An automatic STAR data engine capable of synthesizing images with MMRK to build multi-modal instruction data with reliable chain-of-thought thinking for various STAR tasks and (ii). A comprehsive two-stage capability enhancement training framework, accompanied by a suite of evaluation protocols tailored to different STAR tasks. Based upon these contributions, we introduce STAR-64K, a dataset comprising 64K high-quality multi-modal instruction samples, and conduct experiments across 5 open-source MLLMs. Experimental results show that our two-stage enhancement framework enables smaller 3B/7B models to significantly outperform GPT-4o in STAR. Additionally, we provide in-depth analysis regarding the effectiveness of various designs, data transferability, and scalability.

Related papers

• 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)
• Complementarity-driven Representation Learning for Multi-modal Knowledge Graph Completion [0.0]
  We propose a novel framework named Mixture of Complementary Modality Experts (MoCME)<n>MoCME consists of a Complementarity-guided Modality Knowledge Fusion (CMKF) module and an Entropy-guided Negative Sampling (EGNS) mechanism.<n>Our MoCME achieves state-of-the-art performance, surpassing existing approaches.
  arXiv  Detail & Related papers  (2025-07-28T08:35:11Z)
• Multi-modal Retrieval Augmented Multi-modal Generation: Datasets, Evaluation Metrics and Strong Baselines [63.22096609916707]
  Multi-modal Retrieval Augmented Multi-modal Generation (M$2$RAG) is a novel task that enables foundation models to process multi-modal web content.<n>Despite its potential impact, M$2$RAG remains understudied, lacking comprehensive analysis and high-quality data resources.
  arXiv  Detail & Related papers  (2024-11-25T13:20:19Z)
• MMSci: A Dataset for Graduate-Level Multi-Discipline Multimodal Scientific Understanding [59.41495657570397]
  We present a comprehensive dataset compiled from Nature Communications articles covering 72 scientific fields.<n>We evaluated 19 proprietary and open-source models on two benchmark tasks, figure captioning and multiple-choice, and conducted human expert annotation.<n>Fine-tuning Qwen2-VL-7B with our task-specific data achieved better performance than GPT-4o and even human experts in multiple-choice evaluations.
  arXiv  Detail & Related papers  (2024-07-06T00:40:53Z)
• IWISDM: Assessing instruction following in multimodal models at scale [1.2320972303448239]
  We introduce the instructed-Virtual VISual Decision Making (iWISDM) environment engineered to generate a limitless array of vision-language tasks. Using iWISDM, we compiled three distinct benchmarks of instruction following visual tasks across varying complexity levels. Our findings establish iWISDM as a robust benchmark for assessing the instructional adherence of both existing and emergent multimodal models.
  arXiv  Detail & Related papers  (2024-06-20T14:09:54Z)
• Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning [51.80447197290866]
  Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning.<n>Existing methods focus on crafting elegant entity-wise multi-modal fusion strategies.<n>We introduce a novel framework with Mixture of Modality Knowledge experts (MoMoK) to learn adaptive multi-modal entity representations.
  arXiv  Detail & Related papers  (2024-05-27T06:36:17Z)
• Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts [54.529880848937104]
  We develop a unified MLLM with the MoE architecture, named Uni-MoE, that can handle a wide array of modalities. Specifically, it features modality-specific encoders with connectors for a unified multimodal representation. We evaluate the instruction-tuned Uni-MoE on a comprehensive set of multimodal datasets.
  arXiv  Detail & Related papers  (2024-05-18T12:16:01Z)
• Multi-modal Semantic Understanding with Contrastive Cross-modal Feature Alignment [11.897888221717245]
  This paper proposes a novel CLIP-guided contrastive-learning-based architecture to perform multi-modal feature alignment. Our model is simple to implement without using task-specific external knowledge, and thus can easily migrate to other multi-modal tasks.
  arXiv  Detail & Related papers  (2024-03-11T01:07:36Z)
• StableLLaVA: Enhanced Visual Instruction Tuning with Synthesized Image-Dialogue Data [129.92449761766025]
  We propose a novel data collection methodology that synchronously synthesizes images and dialogues for visual instruction tuning. This approach harnesses the power of generative models, marrying the abilities of ChatGPT and text-to-image generative models. Our research includes comprehensive experiments conducted on various datasets.
  arXiv  Detail & Related papers  (2023-08-20T12:43:52Z)
• MESED: A Multi-modal Entity Set Expansion Dataset with Fine-grained Semantic Classes and Hard Negative Entities [25.059177235004952]
  We propose Multi-modal Entity Set Expansion (MESE), where models integrate information from multiple modalities to represent entities. A powerful multi-modal model MultiExpan is proposed which is pre-trained on four multimodal pre-training tasks. The MESED dataset is the first multi-modal dataset for ESE with large-scale and elaborate manual calibration.
  arXiv  Detail & Related papers  (2023-07-27T14:09:59Z)

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.