GRAM: Group-wise Rank-Aware Model Merging via Subspace Alignment

arXiv cs.AIOctober 22, 2026en

arXiv:2610.29110v1 Announce Type: new Abstract: Merging different models into a single model is highly desirable for multi-task deployment, particularly in regulated domains like healthcare. In such settings, models are often locally fine-tuned due to strict data privacy policies, necessitating that aggregation operates exclusively on the fine-tuned weights. Existing methods apply a uniform merge across all tasks, ignoring the geometric relationships among their learned subspaces. When task updates occupy misaligned subspaces, projecting them onto a shared low-rank basis discards task-relevant directions, a failure mode named \emph{subspace interference}. Through this study, we show that the

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning