Call for Papers
We invite submissions that present original work related to information theory and cognitive systems. We aim to bring together researchers from multiple disciplines (e.g., machine learning, cognitive science, neuroscience, linguistics, economics) who are interested in information-theoretic approaches to human and artificial cognition. This year will feature a special emphasis on connections with researchers focused on the computation/estimation of information-theoretic quantities, with the aim of tightening the collaboration across the machine learning, cognitive science, and information theory communities. We particularly encourage submissions of interdisciplinary work.
Examples of specific topics of interest include but are not limited to:
Novel information-theoretic approaches to cognitive functions (e.g., perception, decision making, language, social reasoning, etc.)
Method and approaches for the validation of information-theoretic formalism in human and artificial cognition
Novel methods and approaches for the computation and/or estimation of information theoretic quantities and their application to human and artificial cognition
Challenges and limitations of the use of information theory in studying cognitive systems
Application of information theory to training human-aligned artificial agents, i.e., agents that can better communicate and cooperate with humans
Format. All papers must be submitted as a single PDF file, limited to a maximum of 4 pages (NeurIPS format) excluding references and acknowledgements. Submissions must be fully anonymized. We ask that authors follow the NeurIPS 2023 formatting guidelines, while using the workshop’s LaTeX style file. Authors may optionally include supplementary materials as an appendix in the submitted PDF, however the reviewers will not be required to consider it for their assessment.
Submission. Please submit via OpenReview at the following link:
https://openreview.net/group?id=NeurIPS.cc/2023/Workshop/InfoCog
The review process will be double-blind. Authors are responsible for making sure their submissions are fully anonymized. Submissions and reviews will not be made public. Only accepted papers will be posted on the workshop’s website. We particularly encourage submissions from groups that are underrepresented at ML conferences based on factors including gender, sexual orientation, race, ethnicity, nationality, disability, and institution.
Dual-submission policy. We welcome submissions describing either ongoing unpublished work, work that is currently under review, or work that has recently been published at a non-ML venue. We discourage submission of work that will be presented at the main conference or that has previously been published at an ML venue. The workshop is considered a non-archival venue and accepted papers will not be part of any official proceedings.
Presentations. All accepted papers will be presented in a poster session during the workshop. A small number of accepted papers will be selected to be presented as contributed talks or spotlights. The workshop will be conducted in-person. We expect to have a limited amount of funding to support a few selected presenters. More details will follow upon acceptance.
Contact information. If you have questions, please contact us at infocog.neurips2023@gmail.com