Objective

The increasing adoption of personalization and recommender systems in high-impact domains raises fundamental questions about how user models represent, reason about, and adapt to human behavior. While recent advances in machine learning have improved predictive accuracy, they offer limited support for explicit reasoning, interpretability, and the incorporation of cognitive and normative constraints. The Second International Workshop on Hybrid AI for Human-Centric Personalization and Recommendation (HyPeR 2026) focuses on hybrid AI as a methodological framework for user modeling, recommendations, and personalization, emphasizing the integration of learning-based approaches with symbolic knowledge, reasoning mechanisms, and cognition-informed representations. HyPeR brings together researchers and practitioners to examine architectures, methods, and evaluation strategies for hybrid user models. The workshop aims to stimulate exchange and to shape future research directions at the intersection of user modeling, hybrid AI, and human-centered recommender systems.

The workshop proposal can be found here.

Important Dates

Event	Date
Paper Submissions	~~August 24, 2026~~ September 7th, 2026
Paper Notifications	September 23, 2026
Workshop date	November 8, 2026

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

Program

Tentative Schedule:

Time (CET)	Title	Authors
14:00 - 14:10	Opening Remarks
14:10 - 15:00	Keynote: What the Item Doesn't Say: Non-Monotonic Personalization in the Era of LLMs	Tommaso Di Noia
15:00 - 15:50	Paper Session 1: Graph-based Reasoning for Personalized Recommendations	Session Chair: Markus Reiter-Haas
15:00 - 15:20	SymKGRec: Neuro-Symbolic Knowledge Graph Reasoning with LLM Alignment for Explainable and Dynamic Personalized Recommendation	Shiteng Cao, Zhiheng Li, Jingwen Liu, Yunlong Gong and Yuankang Liu
15:20 - 15:40	Context-Aware Hybrid AI Reasoning over Enriched Knowledge Graphs for Personalized Recommendations	Marwa Boulakbech
15:40 - 15:50	Episodic Memories for Recommender Systems	Kevin Innerebner, Markus Reiter-Haas and Elisabeth Lex
15:50 - 16:20	Break
16:20 - 17:10	Paper Session 2: Hybrid Representations for Recommender Systems	Session Chair: Elisabeth Lex
16:20 - 16:40	KARMA-Rec: Knowledge-Anchored Collaborative Representation Transfer for Cold-Start Recommendation	Amangel Bhullar and Ziad Kobti
16:40 - 17:00	FOLMind: Logic-Guided Hybrid Representations for Collaborative Recommendation	Raffaele Smalidini, Gianni Carmosino, Dario Di Palma, Alberto Carlo Maria Mancino, Tommaso Di Noia and Fedelucio Narducci
17:00 - 17:10	Agents Over Algorithms for Recommendations? Recommender Integration Strategies for Agentic AI	Markus Reiter-Haas and Elisabeth Lex
17:10 - 17:50	Panel Discussion
17:50 - 18:00	Closing Remarks

Legend: Presentation (research paper) | Presentation (position paper) | Paper Session | Planned Activities

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 recommendation systems
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 using symbolic approaches (e.g., counterfactual fairness)
Mechanisms for dynamic adaptation and symbolic reasoning to handle evolving user preferences and context within hybrid architectures
Evaluation procedures and standardized benchmarks for assessing the performance and robustness of hybrid AI in recommender systems
Behavioral data analysis and user studies of cognition-informed and hybrid modeling approaches
Domain-specific implementations of hybrid AI models in areas such as e-learning, healthcare, finance, and music
Real-world systems and case studies demonstrating hybrid AI architectures for personalized recommendations

Submission Guidelines:

We welcome three types of submissions (in single-column CEUR-WS workshop template):

Full research papers describing mature research results relevant to the workshop topics. Up to 12 pages (excluding references).
Short (Work-in-progress and Demo) Papers describing ongoing research, preliminary research results, or demonstrations relevant to the workshop topics. Up to 6 pages (excluding references).
Position Papers of novel ideas, including position, discussion, reflection, and perspective papers on the workshop topics. Up to 6 pages (excluding references, if needed).

Please use the EasyChair Submission System to submit your contributions. An international panel of experts will review all submissions.

The templates and instructions are available here.

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

Submissions are reviewed in a single-blind peer-review process by at least two members of the program committee based on relevance to the workshop themes, originality, technical quality, clarity, and potential to stimulate discussion