Call for Papers

We invite authors to submit their contributions as extended abstracts. Extended abstracts can take the traditional form of approaching a topic of interest to the workshop and research. We are also interested in submission on study designs (either at conceptualisation, ongoing or submitted) as an opportunity to reflect on the usage of foundation models. The accepted submissions will be presented as lightning talks during the workshop. We welcome submissions related (but not limited) to:

• • Embodiment and Foundation Models:

    • Unique capabilities and challenges for foundation models in physically embodied agents

    • Novel failure modes introduced by embodiment

    • Physical presence influence on user trust, perception, and susceptibility to model limitations

    • How foundation models reshape human-robot relational dynamics

• • Safety Evaluations and Benchmarking:

    • Sycophancy, boundary maintenance, and proactive redirection in social robot interactions

    • LLM safety evaluations to assess risk of physical or psychological harm in embodied contexts

    • Gender, racial, or cultural biases embedded in foundation models used for social robots

    • Evaluation approaches that account for social embodied context

• • Vulnerable Populations:

    • Age-appropriate language and interactions

    • Accessibility in embodied LLMs for users with disabilities

    • Minority languages, multiculturalism, and code-switching

• • Interdisciplinary Methods and Approaches:

    • Evaluation metric co-design

    • Impact of emerging AI regulations on the development and deployment of social robots

    • Impact evaluation in real-world contexts

    • Policy and sustainability aspects

All extended abstracts must be original and not simultaneously submitted to another journal or conference. Abstracts must be no more than 2-3 pages + references. Abstracts should be submitted with the IEEE conference template. 

All abstracts submitted to FoRMA will be peer-reviewed for their novelty, relevance, contribution to the field, and technical soundness. A manuscript will be reviewed by at least two reviewers, who will provide comments. If the abstract is accepted, the authors must submit a revised version that takes into account this feedback. The review process is managed by the workshop chairs. 

Extended abstracts are reviewed using a single-blind review process: authors declare their names and affiliations in the manuscript for the reviewers to see, but reviewers do not know each other’s identities, nor do the authors receive information about who has reviewed their manuscript.

SUBMIT HERE!