Outputs (2296)

ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps (2025)
Presentation / Conference Contribution
Song, X., Yang, X., Yao, C., Ren, J., Bai, R., Chen, X., & Jiang, X. (2025, February). ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps. Presented at The 39th Annual AAAI Conference on Artificial Intelligence, Philadelphia, Pennsylvania, USA

Solving jigsaw puzzles has been extensively studied. While most existing models focus on solving either small-scale puzzles or puzzles with no gap between fragments, solving large-scale puzzles with gaps presents distinctive challenges in both image... Read More about ERL-MPP: Evolutionary Reinforcement Learning with Multi-head Puzzle Perception for Solving Large-scale Jigsaw Puzzles of Eroded Gaps.

Ordinal Exponentiation in Homotopy Type Theory (2025)
Presentation / Conference Contribution
de Jong, T., Kraus, N., Nordvall Forsberg, F., & Xu, C. (2025, June). Ordinal Exponentiation in Homotopy Type Theory. Presented at Fortieth Annual ACM/IEEE Symposium on Logic in Computer Science (LICS 2025), Singapore

We present two seemingly different definitions of constructive ordinal exponentiation, where an ordinal is taken to be a transitive, extensional, and wellfounded order on a set. The first definition is abstract, uses suprema of ordinals, and is solel... Read More about Ordinal Exponentiation in Homotopy Type Theory.

Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design (2025)
Journal Article
Siebers, P.-O. (in press). Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design. Journal of Artificial Societies and Social Simulation,

ChatGPT, the AI-powered chatbot with a massive user base of hundreds of millions, has become a global phenomenon. However, the use of Conversational AI Systems (CAISs) like ChatGPT for research in the field of Social Simulation is still limited. Spec... Read More about Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design.

The graphical theory of monads (2025)
Journal Article
Hinze, R., & Marsden, D. (2025). The graphical theory of monads. Journal of Functional Programming, 35, Article e11. https://doi.org/10.1017/S095679682500005X

The formal theory of monads shows that much of the theory of monads can be developed in the abstract at the level of 2-categories. This means that results about monads can established once and for all, and simply instantiated in settings such as enri... Read More about The graphical theory of monads.

Parallel late acceptance hill-climbing for binary-encoded optimization problems (2025)
Journal Article
Sonuç, E., & Özcan, E. (2025). Parallel late acceptance hill-climbing for binary-encoded optimization problems. International Journal of Optimization and Control: Theories & Applications, 15(2), 110-128. https://doi.org/10.36922/ijocta.1696

This paper presents a Parallel Late Acceptance Hill-Climbing (PLAHC) algorithm for solving binary-encoded optimization problems, with a focus on the Uncapacitated Facility Location Problem (UFLP) and the Maximum Cut Problem (MCP). The experimental re... Read More about Parallel late acceptance hill-climbing for binary-encoded optimization problems.

On the Potential of Fuzzy Integral-based Decision-level Fusion when the Fuzzy Measure is Informed by Densities Alone (2025)
Presentation / Conference Contribution
Huang, Y., & Wagner, C. (2025, July). On the Potential of Fuzzy Integral-based Decision-level Fusion when the Fuzzy Measure is Informed by Densities Alone. Presented at 2025 IEEE International Conference on Fuzzy Systems, Reims, France

Aggregation is key technique in decision-level fusion of classifiers. Beyond affording performance in an ensemble-sense, such aggregation operator based fusion also has the potential to add a substantial layer of interpretability to the overall syste... Read More about On the Potential of Fuzzy Integral-based Decision-level Fusion when the Fuzzy Measure is Informed by Densities Alone.

A User Study Evaluation of Predictive Formal Modelling at Runtime in Human-Swarm Interaction (2025)
Journal Article
Abioye, A. O., Hunt, W., Gu, Y., Schneiders, E., Naiseh, M., Archibald, B., Sevegnani, M., Ramchurn, S. D., Fischer, J. E., & Soorati, M. D. (2025). A User Study Evaluation of Predictive Formal Modelling at Runtime in Human-Swarm Interaction. ACM Transactions on Human-Robot Interaction, 14(4), Article 58. https://doi.org/10.1145/3727989

Formal Modelling is often used as part of the design and testing process of software development to ensure that components operate within suitable bounds even in unexpected circumstances. We conducted a user study evaluation of predictive formal mode... Read More about A User Study Evaluation of Predictive Formal Modelling at Runtime in Human-Swarm Interaction.

Towards More Flexible Fuzzy Membership Functions: Learning from Data (2025)
Presentation / Conference Contribution
Abbasov, F., Chen, C., & Garibaldi, J. M. (2025, July). Towards More Flexible Fuzzy Membership Functions: Learning from Data. Presented at 2025 IEEE International Conference on Fuzzy Systems, Reims, France

Fuzzy systems are widely recognised for their ability to model uncertainty and linguistic knowledge, but their effectiveness often depends on the choice of membership functions. Traditional approaches have relied on membership functions with predefin... Read More about Towards More Flexible Fuzzy Membership Functions: Learning from Data.

A python library for data-driven causal fuzzy classification rule generation --mablars (2025)
Presentation / Conference Contribution
Zhang, T., & Wagner, C. (2025, July). A python library for data-driven causal fuzzy classification rule generation --mablars. Presented at 2025 IEEE International Conference on Fuzzy Systems, Reims, France

A principal focus in fuzzy systems research is on maintaining good performance while providing strong explain-ability, principally by leveraging meaningful sets of human-accessible rules. In practice, while a variety of software tools have been devel... Read More about A python library for data-driven causal fuzzy classification rule generation --mablars.

Counterfactual linguistic rule-based explanations based on locally relevant causal mechanisms (2025)
Presentation / Conference Contribution
Zhang, T., & Wagner, C. (2025, July). Counterfactual linguistic rule-based explanations based on locally relevant causal mechanisms. Presented at 2025 IEEE International Conference on Fuzzy Systems, Reims, France

Counterfactual (CF) explanations provide a potentially powerful mechanism to deliver meaningful explanations of AI decisions. CF explanations are convincing when they reflect causal relationships between variables, because humans are cause-effect thi... Read More about Counterfactual linguistic rule-based explanations based on locally relevant causal mechanisms.