Call for Papers

The R0-FoMo Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models @ NeurIPS 2023 solicits novel contributions that relate broadly to few-shot and zero-shot learning in Large Foundation models, accepting submissions of long and short papers with both empirical and theoretical nature on recent progress in robustness of few-shot or zero-shot learning and its applications. The event will be held on December 15th, 2023. Relevant topics include (but are not limited to):

• In-context learning

• Prompt learning

• Instruction tuning

• Automated evaluation of foundation models

• Parameter Efficient Fine-tuning

• Multilingual foundation models 

• Multimodal foundation models

• Representation learning and self-supervised learning for foundation models

• Responsible AI (Safety, Privacy, Integrity, Fairness, Robustness) using foundation models

• Policy optimization (supervised / reinforced) for foundation models

• Alignment to human preferences

• Human-in-the-loop learning

• Synthetic data generation for/from foundation models

• Unsupervised learning from foundation models

• Adversarial few-shot or zero-shot robustness

• Open problems in few-shot and zero-shot learning of large foundation models

Important Dates

• Paper Submissions Due: Sep 29, 2023 (AOE) Oct 07, 2023 (AOE)

• Notification of Acceptance: Oct 27, 2023

• Camera-ready Paper Due: Nov 17, 2023

• Workshop Date: Dec 15, 2023

Formatting / Submission Instructions 

• Submission URL: https://openreview.net/group?id=NeurIPS.cc/2023/Workshop/R0-FoMo

• Submission Instructions

Papers can be up to 6 pages (7 for camera ready) in NeurIPS submission format (double-blind) [format], excluding references and supplementary material. We allow an unlimited number of pages for references and supplementary material, but reviewers are not required to review the supplementary material. Accepted papers will be presented at the workshop as contributed talks and/or posters. At the discretion of authors, accepted papers can be published through the workshop website.

• Concurrent Submissions

We welcome research papers currently under review at archival NLP and ML conferences (e.g., EMNLP, and ICLR). Submission to this workshop will not break the anonymity or dual submission policies for these conferences. The workshop is non-archival. 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 an area 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.