AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

MAP: Low-compute Model Merging with Amortized Pareto Fronts via Quadratic Approximation

Lu Li, Tianyu Zhang, Zhiqi Bu, Suyuchen Wang, Huan He, Jie Fu, Yonghui Wu, Jiang Bian, Yong Chen, Yoshua Bengio

ICLR 2025 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 9 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
Use MAP instead of the strongest listed merging baselineViT-B/32 model merging · Zero-shot classification, 3–8 taskspreference weighted sum of accuracies: 67.94 $\pm$ 1.79 -> \textbf{69.05$\pm$1.84} (3 tasks); 71.79$\pm$2.93 -> \textbf{72.84$\pm$4.4} (4 tasks); 76.84$\pm$4.7Improved
Use MAP instead of Task ArithmeticViT-B/32 model merging · Zero-shot classification, 2 taskspreference weighted sum of accuracies: 70.73$\pm$1.84 -> 70.7$\pm$1.76No clear effect
Use MAP with 30 or 50 coefficient vectors instead of direct searchViT-B/32 model merging · Zero-shot classification, 2 taskswin rate over direct search: 49.81\% $(\pm 0.30)$Hurt
Use MAP with 30 or 50 coefficient vectors instead of direct searchViT-B/32 model merging · Zero-shot classification, 3 taskswin rate over direct search: 46.90\% $(\pm 0.71)$Hurt
Use MAP instead of sparse direct searchViT-B/32 model merging · Zero-shot classification, 4–8 taskswin rate over direct search: 50.67\% $(\pm 2.44)$ (4 tasks); 53.00\% $(\pm 1.88)$ (5 tasks); 60.71\% $(\pm 1.34)$ (6 tasks); 63.42\% $(\pm 1.91)$ (7 Improved

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