6 papers
PDDLCoder: Agentic PDDL Generation for LLM-Assisted Symbolic Planning
Veit Laule, Jiangtao Shuai, Manfred Hauswirth +1
LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans. Recent hybrid methods instead translate natural language into the…
From USD Scenes to Knowledge Graphs: Zero-Shot Ontology Grounding with LLMs
Jiangtao Shuai, Zongxiong Chen, Manfred Hauswirth +1
Constructing knowledge graphs from 3D simulation scenes is essential for robot task reasoning, but the key bottleneck, grounding scene objects to formal ontology classes, still rel…
NERdME: a Named Entity Recognition Dataset for Indexing Research Artifacts in Code Repositories
Genet Asefa Gesese, Zongxiong Chen, Shufan Jiang +4
Existing scholarly information extraction (SIE) datasets focus on scientific papers and overlook implementation-level details in code repositories. README files describe datasets,…
Post-Training Language Models for Continual Relation Extraction
Sefika Efeoglu, Adrian Paschke, Sonja Schimmler
Real-world data, such as news articles, social media posts, and chatbot conversations, is inherently dynamic and non-stationary, presenting significant challenges for constructing…
NFDI4DSO: Towards a BFO Compliant Ontology for Data Science
Genet Asefa Gesese, Jörg Waitelonis, Zongxiong Chen +2
The NFDI4DataScience (NFDI4DS) project aims to enhance the accessibility and interoperability of research data within Data Science (DS) and Artificial Intelligence (AI) by connecti…
Converter: Enhancing Interoperability in Research Data Management
Sefika Efeoglu, Zongxiong Chen, Sonja Schimmler +1
Research Data Management (RDM) is essential in handling and organizing data in the research field. The Berlin Open Science Platform (BOP) serves as a case study that exemplifies th…