HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

NeurIPSSpotlight2025

Authors: Yu Zhou, Xingyu Wu, Jibin Wu, Liang Feng, KC Tan
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Model merging is a technique that combines multiple large pretrained models into a single model, enhancing performance and broadening task adaptability without original data or additional training…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

← All NeurIPS 2025 Spotlight papers · Browse the whole archive