Related papers: Multi-View Graph Representation Learning for Answe…

Graph Retrieval-Augmented Generation (Graph RAG) effectively builds a knowledge graph (KG) to connect disparate facts across a large document corpus. However, this broad-view approach often lacks the deep structured reasoning needed for…

Multi-hop question answering (QA) necessitates multi-step reasoning and retrieval across interconnected subjects, attributes, and relations. Existing retrieval-augmented generation (RAG) methods struggle to capture these structural…

Universal graph pre-training has emerged as a key paradigm in graph representation learning, offering a promising way to train encoders to learn transferable representations from unlabeled graphs and to effectively generalize across a wide…

Large Language Models (LLMs) often suffer from hallucinations, which Retrieval-Augmented Generation (RAG) and GraphRAG mitigate by incorporating external knowledge and knowledge graphs (KGs). However, GraphRAG remains text-centric due to…

In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE…

Explanation and high-order reasoning capabilities are crucial for real-world visual question answering with diverse levels of inference complexity (e.g., what is the dog that is near the girl playing with?) and important for users to…

Answering questions that require reasoning and aggregation across both structured (tables) and unstructured (raw text) data sources presents significant challenges. Current methods rely on fine-tuning and high-quality, human-curated data,…

Multi-modal Large Language Models (MLLMs) for Visual Question Answering (VQA) often suffer from dual limitations: knowledge hallucination and insufficient fine-grained visual perception. Crucially, we identify that commonsense graphs and…

Multi-hop Question Answering (QA) requires the machine to answer complex questions by finding scattering clues and reasoning from multiple documents. Graph Network (GN) and Question Decomposition (QD) are two common approaches at present.…

With the new generation of satellite technologies, the archives of remote sensing (RS) images are growing very fast. To make the intrinsic information of each RS image easily accessible, visual question answering (VQA) has been introduced…

The increasing availability of multimodal data across text, tables, and images presents new challenges for developing models capable of complex cross-modal reasoning. Existing methods for Multimodal Multi-hop Question Answering (MMQA) often…

When answering complex questions, people can seamlessly combine information from visual, textual and tabular sources. While interest in models that reason over multiple pieces of evidence has surged in recent years, there has been…

Technical reports and articles often contain valuable information in the form of semi-structured data like charts, and figures. Interpreting these and using the information from them is essential for downstream tasks such as question…

Encoding facts as representations of entities and binary relationships between them, as learned by knowledge graph representation models, is useful for various tasks, including predicting new facts, question answering, fact checking and…

Modeling textual or visual information with vector representations trained from large language or visual datasets has been successfully explored in recent years. However, tasks such as visual question answering require combining these…

Visual question answering (VQA) is a challenging task to provide an accurate natural language answer given an image and a natural language question about the image. It involves multi-modal learning, i.e., computer vision (CV) and natural…

We consider the problem of image representation for the tasks of unsupervised learning and semi-supervised learning. In those learning tasks, the raw image vectors may not provide enough representation for their intrinsic structures due to…

The multimodal models used in the emerging field at the intersection of computational linguistics and computer vision implement the bottom-up processing of the `Hub and Spoke' architecture proposed in cognitive science to represent how the…

Multi-hop reading comprehension (RC) across documents poses new challenge over single-document RC because it requires reasoning over multiple documents to reach the final answer. In this paper, we propose a new model to tackle the multi-hop…

Multi-modal knowledge graphs (MKGs) include not only the relation triplets, but also related multi-modal auxiliary data (i.e., texts and images), which enhance the diversity of knowledge. However, the natural incompleteness has…