Efficient Model Specialization via Training-time and Test-time Adaptation

摘要

In this talk, we discuss efficient model specialization algorithm to adapt the pretrained model towards downstream tasks while improving its efficiency, efficiently generalizing to multiple tasks via dynamic architectures, and improving inference-time efficiency utilizing the diversity within model block functionalities. These research directions serve as the foundation towards co-designing models, tasks, systems, and hardware for a reconfigurable efficient intelligence future.