Abstract
Evolutionary model merging enables the creation of high-performing multi-task models but remains computationally prohibitive for consumer hardware. We introduce MERGE3, an efficient framework that makes evolutionary merging feasible on a single GPU by reducing fitness computation costs 50× while preserving performance. MERGE3 achieves this by Extracting a reduced dataset for evaluation, Estimating model abilities using Item Response Theory (IRT), and Evolving optimal merges via IRT-based performance estimators. Our method enables state-of-the-art multilingual and cross-lingual merging, transferring knowledge across languages with significantly lower computational overhead. We provide theoretical guarantees and an open-source library, democratizing high-quality model merging.
Tommaso Mencattini
Research Intern
Adrian R. Minut
PhD Student
Donato Crisostomi
PhD Student
PhD student @ Sapienza, University of Rome | former Applied Science intern @ Amazon Search, Luxembourg | former Research Science intern @ Amazon Alexa, Turin
Andrea Santilli
Research Scientist, Nous Research
PhD Student passionate about natural language processing, representation learning and machine intelligence.
