UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning
UniAR leverages a large multimodal model to generate hierarchical diagnostic descriptions at the word, phrase, and sentence levels, compensating for the lack of paired clinical reports, and demonstrates that it offers a robust and interpretable framework for ASD screening under semantic scarcity.
Lei Xin, Ze-Heng Wang, Jia-Ying Zhu et al.
· 0 citations