Towards deployment-centric multimodal AI beyond vision and language
This work addresses deployment challenges in multimodal AI for researchers and practitioners across disciplines like healthcare and engineering, but it is incremental as it builds on existing data-centric and model-centric approaches.
The paper tackles the problem of multimodal AI being narrowly focused on vision and language with poor deployability, advocating for a deployment-centric workflow that integrates constraints early and broader multimodality to enhance real-world applications.
Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact.