Sample record. Fictional demonstration content.
Abstract
Personalising a model on a user's device requires small, fast-to-train updates. We study rank, placement and quantisation of low-rank adapters on a phone-class model and find that rank 4 on attention projections gives most of the gain at under 2 MB per user.
Keywords adapters · personalisation · low-rank
Full text
CTM-PR-2026-0009.pdf
How to cite
Venkataraman, P. & Holm, A. (2026). Low-Rank Adapters for On-Device Personalisation. In Proceedings of the Symposium on Efficient and On-Device Machine Learning (SEODML 2026) (pp. 27–32). CONTINUUM Proceedings. doi:10.xxxx/ctm.pr.2026.0009