SOURCE-LINKED INTELLIGENCE

Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

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

Read original source ↗ Open in workspace

recordType

paper

region

Global