English

Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU

Multimedia 2026-02-18 v1 Computation and Language Machine Learning

Abstract

Real-time conversational assistants for procedural tasks often depend on video input, which can be computationally expensive and compromise user privacy. For the first time, we propose a real-time conversational assistant that provides comprehensive guidance for a procedural task using only lightweight privacy-preserving modalities such as audio and IMU inputs from a user's wearable device to understand the context. This assistant proactively communicates step-by-step instructions to a user performing a furniture assembly task, and answers user questions. We construct a dataset containing conversations where the assistant guides the user in performing the task. On observing that an off-the-shelf language model is a very talkative assistant, we design a novel User Whim Agnostic (UWA) LoRA finetuning method which improves the model's ability to suppress less informative dialogues, while maintaining its tendency to communicate important instructions. This leads to >30% improvement in the F-score. Finetuning the model also results in a 16x speedup by eliminating the need to provide in-context examples in the prompt. We further describe how such an assistant is implemented on edge devices with no dependence on the cloud.

Keywords

Cite

@article{arxiv.2602.15707,
  title  = {Proactive Conversational Assistant for a Procedural Manual Task based on Audio and IMU},
  author = {Rehana Mahfuz and Yinyi Guo and Erik Visser and Phanidhar Chinchili},
  journal= {arXiv preprint arXiv:2602.15707},
  year   = {2026}
}

Comments

3 figures

R2 v1 2026-07-01T10:40:08.598Z