The SIM Workshop @ ICML2025 solicits novel contributions that relate broadly to large intervention models, accepting submissions of papers with both empirical and theoretical nature on recent progress in predicting effects of novel interventions and distribution shifts by exploiting original ways of composing evidence from multiple data-generation regimes. The event will be held on either July 18 or 19, 2025, contingent upon the finalized ICML schedule. Relevant topics of intersection include (but are not limited to):
causal machine learning
representation learning
distribution shift and domain adaptation
reinforcement learning, bandits and Bayesian optimization
foundations of compositionality in artificial intelligence
application areas such as medical spatial treatments, cell biology, economics, recommender systems, agents, and other relevant topics.
Paper Submissions Due: May 20, 2025 (AOE) extended to May 25, 2025(AOE)
Notification of Acceptance: Jun 09, 2025
Camera-ready Paper Due: Jun 15, 2025
Workshop Date: Jul 18, 2025
Submission URL: https://openreview.net/group?id=ICML.cc/2025/Workshop/SIM
Submission Instructions:
The contributed submission format is of a maximum of 4 pages for the main paper, with unlimited pages for references and appendices in the ICML style format containing original and previously unpublished research. We allow an unlimited number of pages for references and appendices, but reviewers are not required to review the supplementary material in the appendices. Accepted submissions will not be archival, but will be published on our website and on OpenReview. Accepted papers will be presented at the workshop as contributed talks and/or posters.
Concurrent Submissions:
We welcome research papers currently under review at archival AI and ML conferences. Submission to this workshop will not break the anonymity or dual submission policies for these conferences. Please note that we do allow the submission of recently published work. However, when selecting papers for oral presentation, preference is given to original works.
Double-blind reviews:
Submissions will be peer-reviewed by at least 2 reviewers, in addition to a program chair. The reviewing process will be double-blind at the level of the reviewers. As an author, you are responsible for anonymizing your submission. Do not include any authors' names, affiliations, acknowledgements, or any other information that could result in de-anonymization.