The following has IPs at its core. Please consider attending and submitting!
Yours,
Michele
Dear all,
Still deciding between NeurIPS and EurIPS? Maybe this will help!
We are delighted to announce that the 1st Workshop on Epistemic Intelligence in Machine Learning (EIML) will take place in conjunction with EurIPS 2025, this December in Copenhagen, Denmark. The workshop will bring together researchers to discuss the foundations and applications of epistemic uncertainty in machine learning.
We will soon be accepting non-archival submissions (4–6 pages, excluding references and appendices). The deadline for submission is 17th October 2025.
Please find below the detailed Call for Papers. For further information, please check out our workshop website: https://sites.google.com/view/eiml-eurips2025/ [sites.google.com].
We warmly invite you to consider submitting your work and would be grateful if you could also help us disseminate the call within your networks.
Call for Papers: 1st Workshop on Epistemic Intelligence in Machine Learning (EIML) 6th or 7th December 2025 EURIPS 2025, Copenhagen, Denmark. https://sites.google.com/view/eiml-eurips2025/ [sites.google.com]
KEYNOTE SPEAKERS: Prof. Fabio Cuzzolin (Oxford Brokes University, United Kingdom) Prof. Eyke Hüllermeier (Ludwig Maximilian University of Munich (LMU), Germany) Prof. Ryan Martin (NC State University, United States) Prof. Fanny Yang (ETH Zurich, Switzerland)
PANELISTS (In addition to the keynote speakers): Prof. Jason Konek (University of Bristol, United Kingdom) Prof. Gert de Cooman (Ghent University, Belgium)
ORGANISING COMMITEE: Michele Caprio (University of Manchester, United Kingdom) Siu Lun Chau (Nanyang Technological University, Singapore) Ruobin Gong (Rutgers University, United States) Shireen Kudukkil Manchingal (Oxford Brookes University, United Kingdom) Krikamol Muandet (CISPA Helmholz Center for Information Security, Germany) Bob Williamson (University of Tübingen, Germany)
AIMS AND SCOPE: This workshop seeks contributions from researchers across machine learning, statistics, philosophy of science, decision theory, and related disciplines to explore theoretical foundations, algorithmic innovations, and practical applications that center around epistemic uncertainty (EU). We welcome works-in-progress and mature research that address the central challenge of reasoning and decision-making under epistemic uncertainty. Specific topics of interests include, but are not limited to:
Representation and Measurement of Epistemic Uncertainty Mathematical Frameworks for EU: Bayesian methods, imprecise probabilities, fuzzy logic, belief functions, possibility theory, etc. Comparisons and formal properties of uncertainty representations Evaluation criteria and benchmarking strategies for UQ methods. Epistemic v.s. Aleatoric uncertainty: delineation and interaction.
Prediction Under Epistemic Uncertainty Predictive models that capture and express EU: Bayesian models, evidential deep learning, credal models Generalisation under distribution shifts, domain adaptation, and robustness analysis OOD detection and safe prediction under model misspecification Learning under partial or vague supervision
Decision-Making and Learning Under Epistemic Uncertainty Risk-sensitive and ambiguity-aware decision-making frameworks Uncertainty quantification in generative models Active learning, Bayesian experimental design, and uncertainty-aware optimisation EU in reinforcement learning, continual learning, and online learning setting Integration of principled uncertainty models into large-scale architectures (e.g., transformers, diffusion models) Scalable algorithms for traditionally intractable uncertainty models
We encourage both theoretical contributions and applied case studies. Submissions that challenge prevailing assumptions, propose novel benchmarks, or provide insights into the philosophical and foundational dimensions of uncertainty in AI are especially welcome.
Sent from Outlook for iOS<https://aka.ms/o0ukef>