InsTALL: Context-aware Instructional Task Assistance with Multi-modal Large Language Models
This addresses the need for more intelligent and responsive virtual assistants in domains requiring situational awareness, though it is incremental in improving existing multimodal methods.
The paper tackles the problem of building multi-modal virtual assistants that provide real-time, context-aware help for multi-step tasks by observing human actions, achieving state-of-the-art performance in tasks like task recognition and action prediction.
The improved competence of generative models can help building multi-modal virtual assistants that leverage modalities beyond language. By observing humans performing multi-step tasks, one can build assistants that have situational awareness of actions and tasks being performed, enabling them to cater assistance based on this understanding. In this paper, we develop a Context-aware Instructional Task Assistant with Multi-modal Large Language Models (InsTALL) that leverages an online visual stream (e.g. a user's screen share or video recording) and responds in real-time to user queries related to the task at hand. To enable useful assistance, InsTALL 1) trains a multi-modal model on task videos and paired textual data, and 2) automatically extracts task graph from video data and leverages it at training and inference time. We show InsTALL achieves state-of-the-art performance across proposed sub-tasks considered for multimodal activity understanding -- task recognition (TR), action recognition (AR), next action prediction (AP), and plan prediction (PP) -- and outperforms existing baselines on two novel sub-tasks related to automatic error identification.