No AI summary available for this article.
Why It Matters
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by exploiting low-rank structures of task-specific updates, but they commonly assign the same rank capacity to every task. This uniform allocation ignores that task vectors can have heterogeneous spectral complexity, causing the shared merging space to be used suboptimally. In this paper, we propose Spectral Energy-proportional Rank Allocation (SERA), a simple task-a...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.24517v1 · Indexed about 1 hour ago