# Inclusive AI for Group Interactions: Predicting Gaze-Direction Behaviors in People with Intellectual and Developmental Disabilities

arXiv: https://arxiv.org/abs/2603.14460 · HTML: https://mlsanity.com/paper/2603.14460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 26 references that are in the map.
- First posted on arXiv 15 Mar 2026.

## Builds on (most cited first, 5 of 5)

- [Detecting Low Rapport During Natural Interactions in Small Groups from Non-Verbal Behaviour](https://mlsanity.com/paper/1801.06055/) (2018)
- [Human-in-the-loop or AI-in-the-loop? Automate or Collaborate?](https://mlsanity.com/paper/2412.14232/) (2024)
- [VITA: A Multi-modal LLM-based System for Longitudinal, Autonomous, and Adaptive Robotic Mental Well-being Coaching](https://mlsanity.com/paper/2312.09740/) (2023)
- [Conversational Agents in Therapeutic Interventions for Neurodevelopmental Disorders: A Survey](https://mlsanity.com/paper/2112.01146/) (2021)
- [Real-time Addressee Estimation: Deployment of a Deep-Learning Model on the iCub Robot](https://mlsanity.com/paper/2311.05334/) (2023)

## Abstract (arXiv)

Artificial agents that support human group interactions hold great promise, especially in sensitive contexts such as well-being promotion and therapeutic interventions. However, current systems struggle to mediate group interactions involving people who are not neurotypical. This limitation arises because most AI detection models (e.g., for turn-taking) are trained on data from neurotypical populations. This work takes a step toward inclusive AI by addressing the challenge of eye contact detection, a core component of non-verbal communication, with and for people with Intellectual and Developmental Disabilities. First, we introduce a new dataset, Multi-party Interaction with Intellectual and Developmental Disabilities (MIDD), capturing atypical gaze and engagement patterns. Second, we present the results of a comparative analysis with neurotypical datasets, highlighting differences in class imbalance, speaking activity, gaze distribution, and interaction dynamics. Then, we evaluate classifiers ranging from SVMs to FSFNet, showing that fine-tuning on MIDD improves performance, though notable limitations remain. Finally, we present the insights gathered through a focus group with six therapists to interpret our quantitative findings and understand the practical implications of atypical gaze and engagement patterns. Based on these results, we discuss data-driven strategies and emphasize the importance of feature choice for building more inclusive human-centered tools.