Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

22 May 2023

Guillermo Ortiz-Jiménez

Papers citing "Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models"

50 / 88 papers shown

Title
CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging Wenju Sun Qingyong Li Yangli-ao Geng Boyang Li MoMe 19 0 0 11 May 2025
Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning Yeoreum Lee Jinwook Jung Sungyong Baik MoMe 40 0 0 20 Apr 2025
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 51 2 0 15 Apr 2025
Leveraging Submodule Linearity Enhances Task Arithmetic Performance in LLMs Rui Dai Sile Hu Xu Shen Yonggang Zhang Xinmei Tian Jieping Ye MoMe 42 2 0 15 Apr 2025
Exact Unlearning of Finetuning Data via Model Merging at Scale Kevin Kuo Amrith Rajagopal Setlur Kartik Srinivas Aditi Raghunathan Virginia Smith MoMe CLL MU 45 0 0 06 Apr 2025
MASS: MoErging through Adaptive Subspace Selection Donato Crisostomi Alessandro Zirilli Antonio Andrea Gargiulo Maria Sofia Bucarelli Simone Scardapane Fabrizio Silvestri Iacopo Masi Emanuele Rodolà MoMe 40 0 0 06 Apr 2025
Efficient Model Editing with Task-Localized Sparse Fine-tuning Leonardo Iurada Marco Ciccone Tatiana Tommasi KELM MoMe 35 0 0 03 Apr 2025
When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach Vaibhav Rathore S. Bagchi Saikat Dutta Sarthak Mehrotra Zsolt Kira Biplab Banerjee OOD 74 1 0 19 Mar 2025
DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection Chiara Cappellino G. Mancusi Matteo Mosconi Angelo Porrello Simone Calderara Rita Cucchiara ObjD VLM 81 0 0 12 Mar 2025
Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy Wei Junhao Yu Zhe Sakuma Jun AAML MoMe 46 0 0 08 Mar 2025
Multi-Level Collaboration in Model Merging Qi Li Runpeng Yu Xinchao Wang MoMe FedML 86 0 0 03 Mar 2025
Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think Jie Tian Xiaoye Qu Zhenyi Lu Wei Wei Sichen Liu Yu-Xi Cheng DiffM VGen 44 0 0 02 Mar 2025
Scalable Model Merging with Progressive Layer-wise Distillation Jing Xu Jiazheng Li J. Zhang MoMe FedML 83 0 0 18 Feb 2025
Portable Reward Tuning: Towards Reusable Fine-Tuning across Different Pretrained Models Daiki Chijiwa Taku Hasegawa Kyosuke Nishida Kuniko Saito Susumu Takeuchi 36 0 0 18 Feb 2025
Linear Mode Connectivity in Differentiable Tree Ensembles Ryuichi Kanoh M. Sugiyama 60 1 0 17 Feb 2025
Propagation of Chaos for Mean-Field Langevin Dynamics and its Application to Model Ensemble Atsushi Nitanda Anzelle Lee Damian Tan Xing Kai Mizuki Sakaguchi Taiji Suzuki AI4CE 53 1 0 09 Feb 2025
Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging Pierre Ablin Angelos Katharopoulos Skyler Seto David Grangier MoMe 45 0 0 03 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 1 0 28 Jan 2025
Physics of Skill Learning Ziming Liu Yizhou Liu Eric J. Michaud Jeff Gore Max Tegmark 41 0 0 21 Jan 2025
Visual RAG: Expanding MLLM visual knowledge without fine-tuning Mirco Bonomo Simone Bianco VLM 58 5 0 18 Jan 2025
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models Yong-Hyun Park Sangdoo Yun Jin-Hwa Kim Junho Kim Geonhui Jang Yonghyun Jeong Junghyo Jo Gayoung Lee 73 12 0 17 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 83 4 0 10 Jan 2025
Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic Yifei He Yuzheng Hu Yong Lin Tong Zhang Han Zhao FedML MoMe 54 17 0 08 Jan 2025
Parameter-Efficient Interventions for Enhanced Model Merging Marcin Osial Daniel Marczak Bartosz Zieliñski MoMe 82 1 0 22 Dec 2024
SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation Runtao Liu Chen I Chieh Jindong Gu Jipeng Zhang Renjie Pi Qifeng Chen Philip H. S. Torr Ashkan Khakzar Fabio Pizzati EGVM 99 0 0 13 Dec 2024
Task Arithmetic Through The Lens Of One-Shot Federated Learning Zhixu Tao I. Mason Sanjeev R. Kulkarni Xavier Boix MoMe FedML 77 3 0 27 Nov 2024
Is Multiple Object Tracking a Matter of Specialization? G. Mancusi Mattia Bernardi Aniello Panariello Angelo Porrello Rita Cucchiara Simone Calderara MoMe 29 1 0 01 Nov 2024
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging Li Shen A. Tang Enneng Yang G. Guo Yong Luo Lefei Zhang Xiaochun Cao Bo Du Dacheng Tao MoMe 27 5 0 29 Oct 2024
Model merging with SVD to tie the Knots George Stoica Pratik Ramesh B. Ecsedi Leshem Choshen Judy Hoffman MoMe 18 8 0 25 Oct 2024
Closed-form merging of parameter-efficient modules for Federated Continual Learning Riccardo Salami Pietro Buzzega Matteo Mosconi Jacopo Bonato Luigi Sabetta Simone Calderara FedML MoMe CLL 29 2 0 23 Oct 2024
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery Enneng Yang Li Shen Zhenyi Wang G. Guo Xingwei Wang Xiaocun Cao Jie Zhang Dacheng Tao MoMe 24 4 0 18 Oct 2024
Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace Jinluan Yang A. Tang Didi Zhu Zhengyu Chen Li Shen Fei Wu MoMe AAML 50 2 0 17 Oct 2024
CollabEdit: Towards Non-destructive Collaborative Knowledge Editing Jiamu Zheng Jinghuai Zhang Tianyu Du Xuhong Zhang Jianwei Yin Tao Lin KELM 17 0 0 12 Oct 2024
Diversity-Rewarded CFG Distillation Geoffrey Cideron A. Agostinelli Johan Ferret Sertan Girgin Romuald Elie Olivier Bachem Sarah Perrin Alexandre Ramé 34 2 0 08 Oct 2024
NegMerge: Consensual Weight Negation for Strong Machine Unlearning Hyoseo Kim Dongyoon Han Junsuk Choe MoMe MU 18 1 0 08 Oct 2024
What Matters for Model Merging at Scale? Prateek Yadav Tu Vu Jonathan Lai Alexandra Chronopoulou Manaal Faruqui Mohit Bansal Tsendsuren Munkhdalai MoMe 44 12 0 04 Oct 2024
Understanding Reasoning in Chain-of-Thought from the Hopfieldian View Lijie Hu Liang Liu Shu Yang Xin Chen Zhen Tan Muhammad Asif Ali Mengdi Li Di Wang LRM 39 1 0 04 Oct 2024
Parameter Competition Balancing for Model Merging Guodong Du Junlin Lee Jing Li Runhua Jiang Yifei Guo ... Hanting Liu S. Goh Ho-Kin Tang Daojing He Min Zhang MoMe 17 10 0 03 Oct 2024
DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation Changdae Oh Yixuan Li Kyungwoo Song Sangdoo Yun Dongyoon Han OOD MoMe 36 4 0 03 Oct 2024
Disentangling Latent Shifts of In-Context Learning Through Self-Training Josip Jukić Jan Snajder 18 0 0 02 Oct 2024
Foldable SuperNets: Scalable Merging of Transformers with Different Initializations and Tasks Edan Kinderman Itay Hubara Haggai Maron Daniel Soudry MoMe 45 0 0 02 Oct 2024
Layer Swapping for Zero-Shot Cross-Lingual Transfer in Large Language Models Lucas Bandarkar Benjamin Muller Pritish Yuvraj Rui Hou Nayan Singhal Hongjiang Lv Bing-Quan Liu KELM LRM MoMe 26 2 0 02 Oct 2024
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration Mahdi Morafah Vyacheslav Kungurtsev Hojin Chang C. L. P. Chen Bill Lin FedML 22 0 0 27 Sep 2024
Realistic Evaluation of Model Merging for Compositional Generalization Derek Tam Yash Kant Brian Lester Igor Gilitschenski Colin Raffel MoMe 16 5 0 26 Sep 2024
Efficient Pareto Manifold Learning with Low-Rank Structure Weiyu Chen James T. Kwok 21 6 0 30 Jul 2024
Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences Nikolaos Dimitriadis Pascal Frossard F. Fleuret MoE 54 5 0 10 Jul 2024
MagMax: Leveraging Model Merging for Seamless Continual Learning Daniel Marczak Bartłomiej Twardowski Tomasz Trzciñski Sebastian Cygert MoMe CLL 26 17 0 08 Jul 2024
Learning Scalable Model Soup on a Single GPU: An Efficient Subspace Training Strategy Tao Li Weisen Jiang Fanghui Liu X. Huang James T. Kwok MoMe 48 0 0 04 Jul 2024
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling Frederic Z. Zhang Paul Albert Cristian Rodriguez-Opazo Anton van den Hengel Ehsan Abbasnejad MoMe 34 7 0 03 Jul 2024
WARP: On the Benefits of Weight Averaged Rewarded Policies Alexandre Ramé Johan Ferret Nino Vieillard Robert Dadashi Léonard Hussenot Pierre-Louis Cedoz Pier Giuseppe Sessa Sertan Girgin Arthur Douillard Olivier Bachem 47 13 0 24 Jun 2024