Aria-UI is a closed-source agent system developed by University of Hong Kong & Rhymes AI that combines multiple input modalities for computer interaction.
- Integration with GPT-4o
- Multimodal approach
- Joint development by HKU and Rhymes AI
- Aria-UI w/ GPT-4o: 15.15%
- Base Model: GPT-4o integration
- Input: Multiple modalities
- Focus: Computer interaction tasks
- Paper: [Yang et al., '24]
- Citation: https://arxiv.org/abs/2412.16256