Featured image of post Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks

Beyond Text: Utilizing Vocal Cues to Improve Decision Making in LLMs for Robot Navigation Tasks

Better model and token fusion strategy

Info

Comments

Method

  1. They provide vocal features to LLM as evidence for decision making.
  2. They idenfity a specific task and dataset called Disfluent Human Audio-Guided Instructions
Last updated: 2025-05-13
Built with Hugo, theme modified on Stack