Add DIFFA: Large Language Diffusion Models Can Listen and Understand

[JiamingZhou777]

Dear maintainers,

I would like to suggest adding our work "DIFFA: Large Language Diffusion Models Can Listen and Understand" to the Awesome-Audio-LLM repository.

Our paper introduces DIFFA, which explores the capabilities of large language diffusion models in listening and understanding audio. The relevant information is as follows:

• Title: DIFFA: Large Language Diffusion Models Can Listen and Understand
• Paper Link: https://arxiv.org/abs/2507.18452
• Github: https://github.com/NKU-HLT/DIFFA

We believe this work contributes to the field of audio-language models and would be a valuable addition to the collection.

Thank you for your consideration!