Reproduce “Toward a Unified Framework for Collaborative Design of Human-AI Interaction” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Ankur Bhatt, Sven Mayer
The authors propose a conceptual framework for multimodal AI that combines speech, gesture, and gaze to infer intent, explains its suggestions as they are made, and lets users accept, reject, or modify them. Illustrative scenarios show a designer resizing a button and an operator stopping a robot. The paper reports no implementation, user study, or measured improvement.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.