AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

MergOPT: A Merge-Aware Optimizer for Robust Model Merging

Enneng Yang, Qun Yang, Peng Wang, Anke Tang, Guibing Guo, Xiaochun Cao, Li Shen

ICLR 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging

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
fine-tune experts with MergOPT before merging with DAREDARE merging · TraceBench 7 tasks (Llama-3.2-1B)average score: 0.3786 -> 0.4147Improved
fine-tune experts with MergOPT before merging with Task ArithmeticTask Arithmetic · TraceBench 7 tasks (Llama-3.2-3B)average score: 0.4871 -> 0.5045Improved
fine-tune experts with MergOPT before merging with TIES-MergingTIES-Merging · TraceBench 7 tasks (Llama-3.2-3B)average score: 0.4898 -> 0.5098Improved
use MergOPT fine-tuning on Qwen2.5-1.5B with Task ArithmeticTask Arithmetic · TraceBench 7 tasks (Qwen2.5-1.5B)average score: 0.4484 -> 0.4731Improved
use MergOPT at 8B scale (4 tasks)Weight Averaging, Task Arithmetic, TIES, DARE · TraceBench 4 tasks (Llama-3.1-8B)average score: +1.08%, +1.40%, +0.46%, +0.51%Improved
merge fewer tasks (4-task groups) with MergOPTTask Arithmetic · TraceBench 4-task groups (Llama-3.2-1B)average score: 0.3708 -> 0.3851; 0.4959 -> 0.5130Improved
MergOPT fine-tuning changes single-expert performance (before merging)individual experts · TraceBench 7 tasks (Llama-3.2-3B)average score: 0.6057 -> 0.5836Hurt
replace SAFT-Merge (SAM) with MergOPT at equal epochsmerging with Weight Averaging, DARE vs Task Arithmetic, TIES · TraceBench 7 tasks (Llama-3.2-1B)average score: +2.59%, +5.20% vs -2.23%, -1.29%Mixed
replace SAFT-Merge with MergOPT at comparable training timemerging methods · TraceBench 7 tasks (Llama-3.2-1B)average score: +4.08%, +0.70%, +0.95%, +3.99%Improved
tangent-space fine-tuning instead of standard fine-tuningWeight Averaging on ViT-B/32 · CLIP-ViT-B/32 10 tasksaverage accuracy: 54.9 -> 50.5Hurt
MergOPT instead of standard fine-tuning on ViT-B/32 with Weight AveragingWeight Averaging · CLIP-ViT-B/32 10 tasksaverage accuracy: 54.9 -> 56.2Improved
vary Laplace scale b in MergOPT (ablation)Task Arithmetic w/ MergOPT · TraceBench 7 tasks (Llama-3.2-1B)average score: 0.4055 -> 0.4164Improved

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