Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic

8 January 2025

Papers citing "Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic"

6 / 6 papers shown

Title
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers Hongkang Li Yihua Zhang Shuai Zhang M. Wang Sijia Liu Pin-Yu Chen MoMe 57 2 0 15 Apr 2025
Low-Rank and Sparse Model Merging for Multi-Lingual Speech Recognition and Translation Qiuming Zhao Guangzhi Sun Chao Zhang Mingxing Xu Thomas Fang Zheng MoMe VLM 71 0 0 24 Feb 2025
Multi-Task Model Merging via Adaptive Weight Disentanglement Feng Xiong Runxi Cheng Wang Chen Zhanqiu Zhang Yiwen Guo Chun Yuan Ruifeng Xu MoMe 92 4 0 10 Jan 2025
Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks Samuele Poppi Zheng-Xin Yong Yifei He Bobbie Chern Han Zhao Aobo Yang Jianfeng Chi AAML 43 12 0 23 Oct 2024
Robust Multi-Task Learning with Excess Risks Yifei He Shiji Zhou Guojun Zhang Hyokun Yun Yi Tian Xu Belinda Zeng Trishul M. Chilimbi Han Zhao 53 7 0 03 Feb 2024
The Lottery Ticket Hypothesis for Pre-trained BERT Networks Tianlong Chen Jonathan Frankle Shiyu Chang Sijia Liu Yang Zhang Zhangyang Wang Michael Carbin 148 345 0 23 Jul 2020