MVGraph is a new benchmark designed to evaluate large vision‑language models on multi‑graph reasoning tasks where evidence is spread across multiple interrelated visual graph views. It contains 8,000 instances covering eight graph‑theoretic tasks derived from partial and temporal graph scenarios, and each instance is provably unsolvable from a single view. The benchmark also offers 29 diagnostic tasks with 64,000 instances to probe four core capabilities—Perception, Alignment, Composition, and Reasoning—providing golden intermediate representations for detailed analysis.
By Yingjie Zhu, Han Cheng, Xuefeng Bai, Youcheng Pan, Yang Xiang, Kehai Chen
GraphVerse is a new benchmark for multimodal large language models that tests visual graph reasoning by combining perception, graph-based visual inputs, and multi-step reasoning. It introduces Graph-centric Image Editing strategies to actively challenge models while preserving semantics, and offers a VGR-Score metric that evaluates reasoning quality beyond simple answer accuracy. Experiments show current models have limitations in VGR and demonstrate the effectiveness of GraphVerse for broader multimodal reasoning tasks.
By Yuanfu Sun, Yuanhang Ren, Kang Li, Chuanhao Ji, Jiaxi Li, Jiajin Liu, Ninghao Liu, Qiaoyu Tan
arXiv:2608. 05833v1 Announce Type: new Abstract: Knowledge graph completion (KGC) aims to infer missing entities or relations from incomplete graph structures, and has evolved into multimodal knowledge graph completion (MMKGC), where entities are associated with multiple modalities such as text and images.
By Jiafan Li, Mengxue Yang, Jiaqi Zhu, Liang Chang, Ying Li, Hongan Wang
The paper introduces GraphBind, a topology-driven method for multimodal graph foundation models that binds heterogeneous node modalities into a unified shared space using graph topology. By leveraging stable graph structure to organize self and neighborhood semantics, GraphBind adapts this integrated space for both discriminative and generative tasks. Experiments against 11 baselines show that GraphBind outperforms them, achieving up to 28.1% relative improvement on key tasks.
By Xunkai Li, Chenxi Wan, Yinlin Zhu, Wang Luo, Hongchao Qin, Rong-Hua Li, Guoren Wang
The paper shows that large language models (LLMs) naturally organize their hidden state manifolds into small‑world networks, enabling efficient multi‑hop reasoning. By converting similarity matrices into unweighted graphs, the authors trace connectivity between distant semantic anchors and find a sharp topological phase transition: deep reasoning layers compress conceptual distances into paths bounded by six semantic hops, while early syntactic layers remain fragmented. The framework is applied to zero‑shot hallucination detection in Retrieval‑Augmented Generation, revealing that factual generations preserve a ~3‑hop structure, whereas hallucinations collapse the topology.
By Md. Faiyaz Abdullah Sayeedi
arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.
By Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika M\"utze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann
arXiv:2607. 19128v1 Announce Type: new Abstract: Vision-language models (VLMs) provide a unified representation space for textual and visual information, yet their potential as general-purpose backbones for graph-structured data remains largely unexplored.
By Jiayi Yang, Yifang Chen, Yuanfu Sun, Jiajin Liu, Qiaoyu Tan
arXiv:2606. 02673v1 Announce Type: new Abstract: Graphs have been used to enhance large language models (LLMs) for structured reasoning, mostly as external knowledge sources are provided to models at test time.
By Runlin Lei, Xiaokui Xiao, Zhewei Wei
arXiv:2604.26370v2 Announce Type: replace-cross
Abstract: Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-l...
By Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung
ReactBench is a benchmark designed to evaluate the structural reasoning abilities of multimodal large language models (MLLMs) using chemical reaction diagrams. The dataset contains 1,618 expert‑annotated question‑answer pairs that test reasoning across four hierarchical task dimensions, from simple endpoint counting to complex topological analysis. Evaluation of 24 MLLMs shows a performance gap of more than 30% between anchor‑based tasks and holistic structural reasoning tasks, indicating that current models struggle with reasoning over branching, converging, and cyclic structures.
By Qiang Xu, Shengyuan Bai, Yu Wang, He Cao, Leqing Chen, Yuanyuan Liu, Bin Feng, Zijing Liu, Yu Li
arXiv:2607. 28259v1 Announce Type: new Abstract: We introduce Topoformer, a lightweight and scalable framework for graph representation learning that encodes topological structure into attention-friendly sequences.
By Md Joshem Uddin, Astrit Tola, Cuneyt Gurcan Akcora, Baris Coskunuzer
arXiv:2608. 15388v1 Announce Type: new Abstract: Topological deep learning (TDL) methods rely on lifting raw data into higher-order discrete domains such as simplicial complexes, cell complexes, and hypergraphs.
By Mathilde Papillon, Guillermo Bern\'ardez, \'Alvaro Ball\'on Barreiro, Marco Montagna, R\'emi Devaux, Antoine Jardin, Nina Miolane