Call for Papers
We welcome submissions on the following topics:
- Foundations of concept representations and learning in XAI, CRL and NeSy.
- Supervised and unsupervised techniques for learning concepts from observational and interventional data, raw inputs, and pre-trained embeddings.
- Techniques for learning concepts in non-standard settings, e.g., causal abstraction.
- Design and evaluation of concept-based XAI techniques and self-explainable concept-based models.
- Interactive human-machine concept acquisition and alignment.
- Applications of concept-based AI systems, including but not limited to, reasoning, causality, formal verification, interactive learning, and explainability.
- Metrics and evaluation techniques for assessing the quality of learned concepts, with a focus on down-stream applications.
Submissions should present novel, unpublished work. Work that previously appeared in non-archival venues (such as arXiv or other workshops without proceedings) is allowed.
The UCRL workshop is non-archival, and should thus generally not violate dual submission policies at other archival venues (e.g., submitting work that is currently under review at another conference such as NeurIPS is permitted); if unsure, please check yourself with the corresponding venue.
Format
Submissions should be double-blind and formatted using the ICLR latex template and formatting instructions.
Papers should be up to 6 pages in length, including all main results, figures, and tables. Appendices containing additional details are allowed, but reviewers are not expected to take this into account.