@inproceedings{SpLuGeBr25,
	author    = {Jan Speller and Malte Luttermann and Marcel Gehrke and Tanya Braun},
	title     = {{Compression versus Accuracy: A Hierarchy of Lifted Models}},
	booktitle = {Proceedings of the Twenty-Eighth European Conference on Artificial Intelligence (ECAI-2025)},
	year      = {2025},
	pages     = {5051--5058},
	publisher = {{IOS} Press},
}

@inproceedings{SpLuGeBr25,
	author    = {Jan Speller and Malte Luttermann and Marcel Gehrke and Tanya Braun},
	title     = {{Towards Explainability of Approximate Lifted Model Construction: A Geometric Perspective}},
	booktitle = {Proceedings of the Eleventh Workshop on Formal and Cognitive Reasoning (FCR-2025)},
	year      = {2025},
	pages     = {41--56},
	publisher = {{CEUR}},
}

@inproceedings{LuSpGeBrMoHa25,
	author    = {Malte Luttermann and Jan Speller and Marcel Gehrke and Tanya Braun and Ralf Möller and Mattis Hartwig},
	title     = {{Approximate Lifted Model Construction}},
	booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-2025)},
	year      = {2025},
	pages     = {9077--9085},
	publisher = {{IJCAI} Organization},
}

@inproceedings{LuMoGe25,
    author    = {Malte Luttermann and Ralf Möller and Marcel Gehrke},
    title     = {{Lifted Model Construction without Normalisation: A Vectorised Approach to Exploit Symmetries in Factor Graphs}},
    booktitle = {Proceedings of the Third Learning on Graphs Conference (LoG-2024)},
    year      = {2025},
    pages     = {46:1-46:17},
    publisher = {{PMLR}},
}

@article{LuMoGe25,
	author    = {Malte Luttermann and Ralf Möller and Marcel Gehrke},
	title     = {{Lifting Factor Graphs with Some Unknown Factors for New Individuals}},
	journal   = {International Journal of Approximate Reasoning},
	volume    = {179},
	year      = {2025},
	pages     = {109371},
	publisher = {Elsevier},
}

@INPROCEEDINGS{11079485,
  author={Sievers, Thomas and Russwinkel, Nele},
  booktitle={2025 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA)}, 
  title={Using Memory Contents of a Cognitive Model for Prompt Augmentation of a Large Language Model}, 
  year={2025},
  volume={},
  number={},
  pages={172-176},
  keywords={Large language models;Computational modeling;Social robots;Memory management;Decision making;Reliability;Large Language Model;ACT-R;Cognitive Model;Prompt Augmentation;Human-Robot Interaction},
  doi={10.1109/CogSIMA64436.2025.11079485}}

@INPROCEEDINGS{10871032,
  author={Sievers, Thomas},
  booktitle={2025 IEEE/SICE International Symposium on System Integration (SII)}, 
  title={Silence is Golden - Making Pauses in Human Utterances Comprehensible for Social Robots in Human-Robot Interaction *}, 
  year={2025},
  volume={},
  number={},
  pages={526-531},
  keywords={Sentiment analysis;Large language models;Social robots;System integration;Speech recognition;Chatbots;Text to speech},
  doi={10.1109/SII59315.2025.10871032}}

@Article{app15105778,
AUTHOR = {Sievers, Thomas and Russwinkel, Nele},
TITLE = {Retrieving Memory Content from a Cognitive Architecture by Impressions from Language Models for Use in a Social Robot},
JOURNAL = {Applied Sciences},
VOLUME = {15},
YEAR = {2025},
NUMBER = {10},
ARTICLE-NUMBER = {5778},
URL = {https://www.mdpi.com/2076-3417/15/10/5778},
ISSN = {2076-3417},
ABSTRACT = {Large Language Models (LLMs) and Vision-Language Models (VLMs) have the potential to significantly advance the development and application of cognitive architectures for human–robot interaction (HRI) to enable social robots with enhanced cognitive capabilities. An essential cognitive ability of humans is the use of memory. We investigate a way to create a social robot with a human-like memory and recollection based on cognitive processes for a better comprehensible and situational behavior of the robot. Using a combined system consisting of an Adaptive Control of Thought-Rational (ACT-R) model and a humanoid social robot, we show how recollections from the declarative memory of the ACT-R model can be retrieved using data obtained by the robot via an LLM or VLM, processed according to the procedural memory of the cognitive model and returned to the robot as instructions for action. Real-world data captured by the robot can be stored as memory chunks in the cognitive model and recalled, for example by means of associations. This opens up possibilities for using human-like judgment and decision-making capabilities inherent in cognitive architectures with social robots and practically offers opportunities of augmenting the prompt for LLM-driven utterances with content from declarative memory, thus keeping them more contextually relevant. We illustrate the use of such an approach in HRI scenarios with the social robot Pepper.},
DOI = {10.3390/app15105778}
}

@conference{icaart25,
author={Thomas Sievers and Nele Russwinkel and Ralf Möller},
title={Grounding a Social Robot’s Understanding of Words with Associations in a Cognitive Architecture},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={406-410},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013144200003890},
isbn={978-989-758-737-5},
issn={2184-433X},
}