Abstract
Techniques are described for automatic inference of window layouts based on available displays, e.g., based on detecting connection or disconnection of an auxiliary display. Upon detection of a change in display configuration, contextual information regarding active applications, window metadata, and display parameters is obtained, with user permission. Application categories are determined based on semantic analysis. An on-device large language model is utilized to determine an optimal arrangement of windows across the available displays based on the aggregated context and historical usage patterns. Windows are automatically moved and/or resized according to the inferred layout.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Pomini, Aurélien and Zimmermann, Nicolas, "LLM-Driven Dynamical Adaptation of Window Layout Based on Available Displays", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/10135