We welcome original position papers, short papers presenting findings related to bias, as well as case studies and best practices in mitigating harm in multimodal large language models and foundation models. We intend to discuss work around, but not limited to, the following topics.
Submissions may include, but are not limited to:
Bias propagation across modalities (text, image, audio, time-series)
Case studies of stereotypical outputs and misrepresentation in MLLMs
Auditing frameworks and benchmark datasets for multimodal bias evaluation
Inclusive and representative dataset construction for foundation models
Prompt engineering and parameter tuning for bias reduction
Community-driven and participatory design for responsible multimodal AI
Explainability and transparency methods for bias detection
Ethical and policy considerations for fair deployment of multimodal AI
Multidisciplinary and cross-cultural perspectives on representation and fairness
We welcome non-archival submissions in the following formats:
Short Papers (5 – 9 pages): Empirical findings, datasets, or technical analyses.
Long Papers (10 pages): Empirical findings, datasets, or technical analyses.
Position Papers (up to 3 pages): Conceptual arguments or perspectives on representation and equity.
Application Papers (up to 4 pages): Applied or industry examples of bias detection and repair.
All submissions must be in PDF format and use the PMLR format
Accepted papers will be presented at the workshop and included on the official AAAI Community Activities. From the accepted papers, a subset of selected papers will be invited for publication in the Proceedings of Machine Learning Research (PMLR).
Authors of invited papers may choose whether to opt in to PMLR publication.
Please submit your paper via the following link: