Overview
The advent of large foundation models in the realm of AI, including large language models (LLMs), large vision models (LVMs), large multimodal models (LMMs), and diffusion models, has opened new frontiers in various applications. However, deploying these resource-intensive models on edge and mobile devices poses significant challenges due to their limited computing power and storage capacity. Their interaction with mobile devices and applications also needs to be reshaped. This workshop aims to explore the innovative methodologies and advancements for edge and mobile foundation models in two main aspects:
- How to make it feasible to use foundation models in resource-constrained edge/mobile environments.
- How to build killer edge and mobile applications atop foundation models.
Supported by:
