Related papers: mcp-proto-okn: Natural-language access to open sci…

We propose a novel scene graph generation model called Graph R-CNN, that is both effective and efficient at detecting objects and their relations in images. Our model contains a Relation Proposal Network (RePN) that efficiently deals with…

Graph convolutional network (GCN) has been successfully applied to capture global non-consecutive and long-distance semantic information for text classification. However, while GCN-based methods have shown promising results in offline…

Organizations often lay down rules or guidelines called Natural Language Access Control Policies (NLACPs) for specifying who gets access to which information and when. However, these cannot be directly used in a target access control model…

Current Multimodal Large Language Models (MLLMs) rely on centralized architectures and often suffer from poor alignment between the input task and their fixed visual encoding modules, which limits performance on diverse and dynamic visual…

The quality of a knowledge graph directly impacts the quality of downstream applications (e.g. the number of answerable questions using the graph). One ongoing challenge when building a knowledge graph is to ensure completeness and…

The purpose of this work is to describe the Orkg-Leaderboard software designed to extract leaderboards defined as Task-Dataset-Metric tuples automatically from large collections of empirical research papers in Artificial Intelligence (AI).…

In many real-world network datasets such as co-authorship, co-citation, email communication, etc., relationships are complex and go beyond pairwise. Hypergraphs provide a flexible and natural modeling tool to model such complex…

Model Context Protocol (MCP) has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to…

The capabilities of Large Language Models (LLMs) have opened new frontiers for interacting with complex, domain-specific knowledge. However, prevailing methods like Retrieval-Augmented Generation (RAG) and general-purpose Agentic AI, while…

With the recent technological advances, biological datasets, often represented by networks (i.e., graphs) of interacting entities, proliferate with unprecedented complexity and heterogeneity. Although modern network science opens new…

Large Language Models (LLMs) with tool-calling capabilities have demonstrated remarkable potential in executing complex tasks through external tool integration. The Model Context Protocol (MCP) has emerged as a standardized framework for…

Purpose: Cyber-Physical Systems (CPSs) integrate computation and physical processes, producing time series data from thousands of sensors. Knowledge graphs can contextualize these data, yet current approaches that are applicably to…

We present CONAN (COde for exoplaNet ANalysis), an open-source Python package for comprehensive analyses of exoplanetary systems. It provides a unified Bayesian framework to simultaneously analyze diverse exoplanet datasets to derive global…

Soil organic carbon is crucial for climate change mitigation and agricultural sustainability. However, understanding its dynamics requires integrating complex, heterogeneous data from multiple sources. This paper introduces the Soil Organic…

Recent applications of deep convolutional neural networks in medical imaging raise concerns about their interpretability. While most explainable deep learning applications use post hoc methods (such as GradCAM) to generate feature…

OpenML is an online platform for open science collaboration in machine learning, used to share datasets and results of machine learning experiments. In this paper we introduce OpenML-Python, a client API for Python, opening up the OpenML…

Knowledge graphs use nodes, relationships, and properties to represent arbitrarily complex data. When stored in a graph database, the Cypher query language enables efficient modeling and querying of knowledge graphs. However, using Cypher…

Heterogeneous graph neural networks (HGNNs) were proposed for representation learning on structural data with multiple types of nodes and edges. To deal with the performance degradation issue when HGNNs become deep, researchers combine…

Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole, while the implicit semantic associations behind highly complex interactions of…

We present CryptGNN, a secure and effective inference solution for third-party graph neural network (GNN) models in the cloud, which are accessed by clients as ML as a service (MLaaS). The main novelty of CryptGNN is its secure message…