Published July 13, 2026
| Version v1
Preprint
Open
Adaptive Dual Distillation for On-Device Personalized Language Models: A Conceptual Framework and Feasibility Protocol
Authors/Creators
Description
We propose a conceptual framework called ADDT that integrates general knowledge compression with local personalization in a single architecture executable on consumer devices. The framework integrates five components: knowledge distillation, preference distillation, style distillation, a retrieval-based memory layer, and continuous updates. We define digital twin in a narrow functional sense (an alignment tool, not an identity representation), and present UIS as an exploratory tool
under validation. This paper is targeted at specialized workshops or as an arXiv preprint, not as a results paper for a main track.