Objective

Hybrid AI, which integrates symbolic and sub-symbolic methods, has emerged as a promising paradigm for advancing human-centric personalization. By combining machine learning with structured knowledge representations, hybrid AI enables interpretable and adaptive user models that account for complex human factors such as biases, mental models, and affective states. The HyPer workshop focuses on how hybrid AI approaches—combining neural architectures, symbolic representations, and cognitive/behavioral frameworks—can foster more explainable and personalized user experiences. Specifically, we aim to explore innovative applications of hybrid AI in personalization, bridging the gap between explainability, cognitive modeling, and automated adaptation to user preferences. The HyPer workshop will provide a venue for researchers and practitioners to discuss the latest advancements, challenges, and future directions in this interdisciplinary field.

The workshop proposal can be found here.

Important Dates

Event Date
Submission Site Open March 6, 2025
Paper Submissions April 9, 2025 April 16, 2025
Paper Notifications April 28, 2025 April 30, 2025
Camera-ready Submission May 5, 2025
Workshop date June 16, 2025

All deadlines are at 11:59 pm AoE (Anywhere on Earth).

Program

Time (EDT) Session Authors
09:00 - 09:10 Opening Remarks
09:10 - 09:35 Towards a Hybrid Framework for Motion Representation and Analysis based on Labanotation and LMA (Paper #340, LONG) Roberto Perez-Martinez, Alberto Casas-Ortiz and Olga C. Santos
09:35 - 09:50 Differentiable Fuzzy Neural Networks for Recommender Systems (Paper #321, SHORT) Stephan Bartl, Kevin Innerebner and Elisabeth Lex
09:50 - 10:15 The Impact of Confidence Ratings on User Trust in Large Language Models (Paper #337, LONG) Lifei Wang, Natalie Friedman, Chengchao Zhu, Zeshu Zhu and S.Joy Mountford
10:15 - 10:30 Procedural Memory is not All You Need: Bridging Cognitive Gaps in LLM-Based Agents (Paper #260, SHORT) Schaun Wheeler and Olivier Jeunen
10:30 - 11:00 Break
11:00 - 11:25 User Orientations and Stage-Specific Behaviors in E-commerce Exploratory Search: A Formative Study (Paper #339, LONG) Eunhye Kim, Kiroong Choe, Guangjing Yan and Mingyu Kang
11:25 - 11:50 The Potential of AutoML for Recommender Systems (Paper #271, LONG) Tobias Vente and Joeran Beel
11:50 - 12:05 Hybrid Personalization Using Declarative and Procedural Memory Modules of the Cognitive Architecture ACT-R (Paper #335, SHORT) Kevin Innerebner, Dominik Kowald, Markus Schedl and Elisabeth Lex
12:05 - 12:20 Building Human-AI Reliance Through Cognitive Engagement and Exploratory AI Assistance (Paper #232, SHORT) Muhammad Raees, Vassilis-Javed Khan and Konstantinos Papangelis
12:20 - 12:30 Closing Remarks

Legend: Presentation (long paper) | Presentation (short paper) | Break | Opening & Closing

Call for Contributions

The Hyper workshop aims to bridge the gap between sub-symbolic learning (e.g., neural networks) and symbolic knowledge representations (e.g., knowledge graphs, ontologies, logic-based models) to develop hybrid user models that better reflect human cognitive processes, social behaviors, and decision-making patterns.

We invite research papers (short and long), extended abstracts, and position papers relevant to the workshop topics, which include, but are not limited to:

  • Methods for integrating symbolic knowledge and sub-symbolic learning in user modeling
  • Applications of cognitive theories and behavioral insights in hybrid AI models for personalization
  • Techniques for interpretability, explainability, and trust in hybrid AI systems
  • Methods for detecting and mitigating biases and unfairness in hybrid AI, e.g., by using symbolic approaches such as counterfactual fairness
  • Behavioral data analysis and user studies of cognitively-inspired modeling approaches Domain-specific implementations of hybrid AI models (e.g., e-learning, healthcare, finance, music)

Submission Guidelines:

We welcome three types of submissions:

  1. Full research papers describing mature research results relevant to the workshop topics. Up to 8 pages (including references).
  2. Work-in-progress and Demo Papers describing ongoing research, preliminary research results, or demonstrations relevant to the workshop topics. Up to 6 pages (including references).
  3. Position and Perspective Papers, including position, discussion, reflection, and perspective papers on the workshop topics. Up to 4 pages (including references, if needed).

Please use the EasyChair Submission System to submit your contributions, selecting the “HyPer- Hybrid AI for Human-Centric Personalization” track. An international panel of experts will review all submissions.

Papers must be formatted according to the new workflow for ACM publications. All accepted papers will be published by ACM and will be available via the ACM Digital Library. At least one author of each accepted paper must register for the particular workshop and present the paper there.

The templates and instructions are available here.

If you work with Overleaf, you can directly start with the template from here.

Organizers and Program Committee

Organizers

Program Committee

  • Florian Atzenhofer-Baumgartner, University of Graz
  • Toine Bogers, IT University of Copenhagen
  • Tomislav Duricic, Know-Center GmbH
  • Hannah Eckert, Johannes Kepler Universität Linz
  • Emanuel Lacic, Infobip
  • Peter Müllner, Know-Center GmbH
  • Julia Neidhardt, TU Vienna
  • Özlem Özgöbek, Norwegian University of Science and Technology
  • Markus Reiter-Haas, Duke University