Localizing Task Information for Improved Model Merging and Compression

Localizing Task Information for Improved Model Merging and Compression

13 May 2024

Nikolaos Dimitriadis

Guillermo Ortiz-Jimenez

Franccois Fleuret

Pascal Frossard

Papers citing "Localizing Task Information for Improved Model Merging and Compression"

14 / 14 papers shown

Title
SEA-LION: Southeast Asian Languages in One Network Raymond Ng Thanh Ngan Nguyen Yuli Huang Ngee Chia Tai Wai Yi Leong ... David Ong Tat-Wee B. Liu William-Chandra Tjhi Erik Cambria Leslie Teo 36 11 0 08 Apr 2025
RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment Chao Wang Giulio Franzese A. Finamore Pietro Michiardi 64 0 0 18 Mar 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
Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging Zhixiang Wang Zhenyu Mao Yixuan Qiao Yunfang Wu Biye Li MoMe 73 0 0 17 Feb 2025
Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts Wenju Sun Qingyong Li Wen Wang Yangli-ao Geng Boyang Li 36 2 0 28 Jan 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
Task Singular Vectors: Reducing Task Interference in Model Merging Antonio Andrea Gargiulo Donato Crisostomi Maria Sofia Bucarelli Simone Scardapane Fabrizio Silvestri Emanuele Rodolà MoMe 87 8 0 26 Nov 2024
ATM: Improving Model Merging by Alternating Tuning and Merging Luca Zhou Daniele Solombrino Donato Crisostomi Maria Sofia Bucarelli Fabrizio Silvestri Emanuele Rodolà MoMe 37 4 0 05 Nov 2024
Agent Skill Acquisition for Large Language Models via CycleQD So Kuroki Taishi Nakamura Takuya Akiba Yujin Tang MoMe 29 0 0 16 Oct 2024
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences Nikolaos Dimitriadis Pascal Frossard F. Fleuret MoE 57 6 0 10 Jul 2024
LCM-LoRA: A Universal Stable-Diffusion Acceleration Module Simian Luo Yiqin Tan Suraj Patil Daniel Gu Patrick von Platen Apolinário Passos Longbo Huang Jian Li Hang Zhao MoMe 108 139 0 09 Nov 2023
Efficiently Identifying Task Groupings for Multi-Task Learning Christopher Fifty Ehsan Amid Zhe Zhao Tianhe Yu Rohan Anil Chelsea Finn 201 235 1 10 Sep 2021
The Power of Scale for Parameter-Efficient Prompt Tuning Brian Lester Rami Al-Rfou Noah Constant VPVLM 278 3,784 0 18 Apr 2021
Pruning and Quantization for Deep Neural Network Acceleration: A Survey Tailin Liang C. Glossner Lei Wang Shaobo Shi Xiaotong Zhang MQ 124 665 0 24 Jan 2021