Generative artificial intelligence (GenAI) refers to technology that leverages large language models to generate content in response to human prompts and it is being increasingly used in school classrooms. The potential of GenAI for supporting learning experiences and outcomes of neurodiverse students is not yet fully known. A systematic literature review was conducted to identify empirical research which has investigated the application of GenAI in neurodiverse student populations at school. The approaches and outcomes of each study were analysed within the lens of Universal Design for Learning (UDL) and Strengths-Based Differentiated Instruction (SB-DI). The analysis suggested that GenAI can support some elements related to the three main principles of UDL (Representation, Action and Expression, Engagement). First, to create diverse formats of information (e.g., concept maps and summaries) thereby supporting multiple means of representation. Second, to provide feedback (e.g., on writing and language learning) thereby supporting multiple means of action and expression. Third, to personalise learning, provide novel challenges, and foster interest thereby supporting multiple means of engagement. GenAI also showed evidence of supporting SB-DI strategies through the capacity to identify and leverage strengths, provide individualised support, and address challenges in learning. However, the analysis also showed that GenAI requires careful implementation with neurodiverse students to ensure that it is used safely and ethically, gives accurate information, and complements, rather than replaces, effective teaching practices. Further research is needed given the small number of studies conducted to date and needs to include more diverse populations and stronger study designs. Nevertheless, utilising UDL's proactive design principles with strengths-based differentiation strategies provides a flexible framework to harness the benefits of GenAI for neurodiverse students.

Keywords: Neurodiverse students, artificial intelligence, generative AI, universal design for learning, differentiated instruction.