RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

NeurIPSSpotlight2025

Authors
Fanhu Zeng, Haiyang Guo, Fei Zhu, Li Shen, Hao Tang
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

fine-tuning robustness efficient llm

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive