@article{lex2025hybrid,
  title={Hybrid AI for Human-Centric Personalization (HyPer)},
  author={Lex, Elisabeth and Innerebner, Kevin and Tkalcic, Marko and Kowald, Dominik and Schedl, Markus},
  year={2025}
}

@inproceedings{simader2025ferat,
  title={FERAT: A New Expansion-Based Certification Framework for Quantified Boolean Formulas},
  author={Simader, Marcel and Rebola-Pardo, Adrian and Seidl, Martina},
  booktitle={Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing},
  pages={1043--1050},
  year={2025}
}

@misc{presutti2025opportunities,
  title={Opportunities for Knowledge Graphs in the AI landscape-An application-centric perspective},
  author={Presutti, Valentina and Motta, Enrico and Sabou, Marta},
  journal={Journal of Web Semantics},
  pages={100867},
  year={2025},
  publisher={Elsevier}
}

@inproceedings{chatterjee2025value,
  title={Value Iteration with Guessing for Markov Chains and Markov Decision Processes},
  author={Chatterjee, Krishnendu and JafariRaviz, Mahdi and Saona, Raimundo and Svoboda, Jakub},
  booktitle={International Conference on Tools and Algorithms for the Construction and Analysis of Systems},
  pages={217--236},
  year={2025},
  organization={Springer}
}

@inproceedings{chatterjee2025refuting,
  title={Refuting Equivalence in Probabilistic Programs with Conditioning},
  author={Chatterjee, Krishnendu and Kafshdar Goharshady, Ehsan and Novotn{\`y}, Petr and {\v{Z}}ikeli{\'c}, {\DJ}or{\dj}e},
  booktitle={International Conference on Tools and Algorithms for the Construction and Analysis of Systems},
  pages={279--300},
  year={2025},
  organization={Springer}
}

@article{ekaputra2025pattern,
  title={Pattern-based engineering of Neurosymbolic AI Systems},
  author={Ekaputra, Fajar J},
  journal={Journal of Web Semantics},
  volume={85},
  pages={100855},
  year={2025},
  publisher={Elsevier}
}

@article{tsanevaknowledge,
  title={Knowledge Engineering with Large Language Models: A Capability Assessment in Ontology Evaluation},
  author={Tsaneva, Stefani and Herwanto, Guntur Budi and Llugiqi, Majlinda and Sabou, Marta}
}

@article{schimunek2025mhnfs,
  title={MHNfs: Prompting In-Context Bioactivity Predictions for Low-Data Drug Discovery},
  author={Schimunek, Johannes and Luukkonen, Sohvi and Klambauer, Günter},
  journal={Journal of Chemical Information and Modeling},
  year={2025},
  publisher={ACS Publications}
}

@inproceedings{hausberger2025exim,
  title={ExIM: Exploring Intent of Music Listening for Retrieving User-generated Playlists},
  author={Hausberger, Anna and Strauss, Hannah and Schedl, Markus},
  booktitle={Proceedings of the 2025 ACM SIGIR Conference on Human Information Interaction and Retrieval},
  pages={348--357},
  year={2025}
}

@article{chatterjee2025liquid,
  title={When is liquid democracy possible? On the manipulation of variance.},
  author={Chatterjee, Krishnendu and Gilbert, Seth and Schmid, Stefan and Svoboda, Jakub and Yeo, Michelle},
  journal={Cryptology ePrint Archive},
  year={2025}
}

@inproceedings{ahmetaj2025common,
  title={Common Foundations for SHACL, ShEx, and PG-Schema},
  author={Ahmetaj, Shqiponja and Boneva, Iovka and Hidders, Jan and Hose, Katja and Jakubowski, Maxime and Labra Gayo, Jose Emilio and Martens, Wim and Mogavero, Fabio and Murlak, Filip and Okulmus, Cem and others},
  booktitle={Proceedings of the ACM on Web Conference 2025},
  pages={8--21},
  year={2025}
}

@inproceedings{koroglu2025towards,
  title={Towards Improving Automated Testing with GraphWalker},
  author={Koroglu, Yavuz and Beyaz{\i}t, Mutlu and Kilincceker, Onur and Demeyer, Serge and Wotawa, Franz},
  booktitle={2025 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)},
  pages={54--58},
  year={2025},
  organization={IEEE}
}

@article{
doi:10.1073/pnas.2423072122,
author = {Simone Bombari  and Marco Mondelli },
title = {Privacy for free in the overparameterized regime},
journal = {Proceedings of the National Academy of Sciences},
volume = {122},
number = {15},
pages = {e2423072122},
year = {2025},
doi = {10.1073/pnas.2423072122},
URL = {https://www.pnas.org/doi/abs/10.1073/pnas.2423072122},
eprint = {https://www.pnas.org/doi/pdf/10.1073/pnas.2423072122},
abstract = {In many deep learning applications, training datasets routinely include personal, sensitive information. Learning from these data is possible without creating privacy infringement via methods guaranteeing differential privacy, designed to provide provable protection to any individual user. However, differential privacy comes with a performance cost, and the cost is often believed to grow with the number of parameters of the learning model. Our work challenges this view, showing that overparameterization is not at odds with privacy. In fact, we prove that, for a class of overparameterized models having access to enough training samples, privacy even comes for free, i.e., with a small loss in performance. This result provides theoretical support to the development of differentially private models at scale. Differentially private gradient descent (DP-GD) is a popular algorithm to train deep learning models with provable guarantees on the privacy of the training data. In the last decade, the problem of understanding its performance cost with respect to standard GD has received remarkable attention from the research community, which has led to upper bounds on the excess population risk RP in different learning settings. However, such bounds typically degrade with overparameterization, i.e., as the number of parameters p gets larger than the number of training samples n—a regime which is ubiquitous in current deep-learning practice. As a result, the lack of theoretical insights leaves practitioners without clear guidance, leading some to reduce the effective number of trainable parameters to improve performance, while others use larger models to achieve better results through scale. In this work, we show that in the popular random features model with quadratic loss, for any sufficiently large p, privacy can be obtained for free, i.e., RP=o(1), not only when the privacy parameter ε has constant order but also in the strongly private setting ε=o(1). This challenges the common wisdom that overparameterization inherently hinders performance in private learning.}}
}

@inproceedings{adam2025asp,
  title={ASP-Driven Emergency Planning for Norm Violations in Reinforcement Learning},
  author={Adam, Sebastian and Eiter, Thomas},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={14},
  pages={14772--14780},
  year={2025}
}

@inproceedings{janota2025breaking,
  title={Breaking symmetries in quantified graph search: A comparative study},
  author={Janota, Mikol{\'a}{\v{s}} and Kirchweger, Markus and Peitl, Tom{\'a}{\v{s}} and Szeider, Stefan},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={11},
  pages={11246--11254},
  year={2025}
}

@inproceedings{ganian2025parameterized,
  title={Parameterized Complexity of Caching in Networks},
  author={Ganian, Robert and Mc Inerney, Fionn and Tsigkari, Dimitra},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={11},
  pages={11229--11237},
  year={2025}
}

@inproceedings{chatterjee2025quantified,
  title={Quantified Linear and Polynomial Arithmetic Satisfiability via Template-based Skolemization},
  author={Chatterjee, Krishnendu and Goharshady, Ehsan Kafshdar and Karrabi, Mehrdad and Motwani, Harshit J and Seeliger, Maximilian and {\v{Z}}ikeli{\'c}, {\DJ}or{\dj}e},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={11},
  pages={11158--11166},
  year={2025}
}

@inproceedings{deligkas2025complexity,
  title={The Complexity of Extending Fair Allocations of Indivisible Goods},
  author={Deligkas, Argyrios and Eiben, Eduard and Ganian, Robert and Goldsmith, Tiger-Lily and Ioannidis, Stavros D},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={13},
  pages={13745--13753},
  year={2025}
}

@inproceedings{chatterjee2025linear,
  title={Linear Equations with Min and Max Operators: Computational Complexity},
  author={Chatterjee, Krishnendu and Luo, Ruichen and Saona, Raimundo and Svoboda, Jakub},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={39},
  number={11},
  pages={11150--11157},
  year={2025}
}

@article{plank2025solution,
  title={Solution Counts of Some Prominent Quantified Boolean Formulas Families},
  author={Plank, Andreas and Kauers, Manuel and Seidl, Martina},
  year={2025}
}

@inproceedings{avarikioti2024route,
  title={Route discovery in private payment channel networks},
  author={Avarikioti, Zeta and Bastankhah, Mahsa and Maddah-Ali, Mohammad Ali and Pietrzak, Krzysztof and Svoboda, Jakub and Yeo, Michelle},
  booktitle={European Symposium on Research in Computer Security},
  pages={207--223},
  year={2024},
  organization={Springer}
}

@incollection{baldazzi2025knowledge,
  title={Knowledge Graph-Based Reasoning in Large Language Models},
  author={Baldazzi, Teodoro and Bellomarini, Luigi and Sallinger, Emanuel},
  booktitle={Handbook on Neurosymbolic AI and Knowledge Graphs},
  pages={441--465},
  year={2025},
  publisher={IOS Press}
}

@article{schweiger2025impact,
  title={The impact of playlist characteristics on coherence in user-curated music playlists},
  author={Schweiger, Harald and Parada-Cabaleiro, Emilia and Schedl, Markus},
  journal={EPJ Data Science},
  volume={14},
  number={1},
  pages={24},
  year={2025},
  publisher={Springer Berlin Heidelberg}
}

@inproceedings{ielanskyiaddressing,
  title={Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation},
  author={Ielanskyi, Mykyta and Schweighofer, Kajetan and Aichberger, Lukas and Hochreiter, Sepp},
  booktitle={ICLR Workshop: Quantify Uncertainty and Hallucination in Foundation Models: The Next Frontier in Reliable AI}
}

@article{bergougnoux2023space,
  title={Space-efficient parameterized algorithms on graphs of low shrubdepth},
  author={Bergougnoux, Benjamin and Chekan, Vera and Ganian, Robert and Kant{\'e}, Mamadou Moustapha and Mnich, Matthias and Oum, Sang-il and Pilipczuk, Micha{\l} and van Leeuwen, Erik Jan},
  journal={ACM Transactions on Computation Theory},
  year={2023},
  publisher={ACM New York, NY}
}

@article{waltersdorfer2025leveraging,
  title={Leveraging Knowledge Graphs for AI System Auditing and Transparency},
  author={Waltersdorfer, Laura and Sabou, Marta},
  journal={Journal of Web Semantics},
  volume={84},
  pages={100849},
  year={2025},
  publisher={Elsevier}
}

@inproceedings{schmolliadversarially,
  title={Adversarially Robust Spiking Neural Networks with Sparse Connectivity},
  author={Schmolli, Mathias and Baronig, Maximilian and Legenstein, Robert and Ozdenizci, Ozan},
  booktitle={The Second Conference on Parsimony and Learning (Proceedings Track)}
}

@article{wu2025simple,
  title={A simple model for Behavioral Time Scale Synaptic Plasticity (BTSP) provides content addressable memory with binary synapses and one-shot learning},
  author={Wu, Yujie and Maass, Wolfgang},
  journal={Nature communications},
  volume={16},
  number={1},
  pages={342},
  year={2025},
  publisher={Nature Publishing Group UK London}
}

@inproceedings{poppel2025flashrnn,
  title={FlashRNN: I/O-aware optimization of traditional RNNs on modern hardware},
  author={P{\"o}ppel, Korbinian and Beck, Maximilian and Hochreiter, Sepp},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}

@inproceedings{aichberger2025improving,
  title={Improving uncertainty estimation through semantically diverse language generation},
  author={Aichberger, Lukas and Schweighofer, Kajetan and Ielanskyi, Mykyta and Hochreiter, Sepp},
  booktitle={The Thirteenth International Conference on Learning Representations},
  year={2025}
}

@inproceedings{ozdenizciprivacy,
  title={Privacy-Aware Lifelong Learning},
  author={Ozdenizci, Ozan and Rueckert, Elmar and Legenstein, Robert},
  booktitle={The Thirteenth International Conference on Learning Representations}
}

@inproceedings{ganiantraining,
  title={Training One-Dimensional Graph Neural Networks is NP-Hard},
  author={Ganian, Robert and Rocton, Mathis and Wietheger, Simon},
  booktitle={The Thirteenth International Conference on Learning Representations}
}

@article{herwanto2025ontology,
  title={Ontology Corpora for LLM-based Knowledge Engineering Research},
  author={Herwanto, Guntur Budi and Tsaneva, Stefani and Sabou, Marta},
  year={2025}
}