Call for Papers
We welcome submissions related to any aspects of CRL, including but not limited to:
- Causal representation learning, including self-supervised, multi-modal or multi-environment CRL, either in time series or in an atemporal setting, observational or interventional
- Causality-inspired representation learning, including learning representations that are only approximately causal, but still useful in terms of generalization or transfer learning
- Abstractions of causal models or in general multi-level causal systems
- Connecting CRL with system identification, learning differential equations from data or sequences of images, or in general connections to dynamical systems
- Theoretical works on identifiability in representation learning broadly
- Real-world applications of CRL, e.g. in biology, healthcare, (medical) imaging or robotics; including new benchmarks or datasets, or addressing the gap from theory to practice
Submissions should present novel, unpublished work.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 CRL workshop is non-archival, and should thus generally not violate dual submission policies at other archival venues; if unsure, please check yourself with the corresponding venue.