AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

FREE-Merging: Fourier Transform for Efficient Model Merging

Shenghe Zheng, Hongzhi Wang

ICCV 2025 · Large language models › Instruction and fine-tuning · approach: Efficient LLM fine-tuning systems · 21 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add FR-Merging high-pass filtering (ablation)backbone · ViT-B/32 8 tasksavg accuracy: 70.10 -> 76.96Improved
add FR-Merging high-pass filtering (ablation)backbone · ViT-L/14 8 tasksavg accuracy: 84.50 -> 88.21Improved
add Eq.3 merging coefficients (ablation)FR-Merging · ViT-B/32 8 tasksavg accuracy: 76.96 -> 78.10Improved
add top-K experts without rescaling (ablation)backbone · ViT-B/32 8 tasksavg accuracy: 70.10 -> 65.24Hurt
add rescaling to top-K experts (ablation)FREE-Merging · ViT-B/32 8 tasksavg accuracy: 79.38 -> 89.68Improved
add FR-Merging (ablation)Ties-Merging · ViT-B/32 8 tasksavg accuracy: 73.6 -> 78.3Improved
add FR-Merging (ablation)Breadcrumbs · ViT-B/32 8 tasksavg accuracy: 75.0 -> 78.8Improved
add FR-Merging (ablation)TSVM · ViT-L/14 8 tasksavg accuracy: 91.9 -> 92.5Improved
add FR-Merging (ablation)TSVM · ViT-B/32 8 tasksavg accuracy: 83.9 -> 84.8Improved
replace PCB-Merging with FR-Mergingcost-free merging · ViT-B/32 8 tasksavg accuracy: 75.8 -> 78.1Improved
replace Twin-Merging with FREE-Mergingexpert-based merging · ViT-L/14 8 tasksavg accuracy: 92.7 -> 93.7Improved
replace Twin-Merging with FREE-Mergingexpert-based merging · 30 vision tasksavg accuracy: 75.52 -> 79.67Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy