v1v2v3 (latest)

Editing Models with Task Arithmetic

International Conference on Learning Representations (ICLR), 2022

8 December 2022

ArXiv (abs)PDF HTML HuggingFace (7 upvotes)

Papers citing "Editing Models with Task Arithmetic"

50 / 524 papers shown

Title
Learning without training: The implicit dynamics of in-context learning Benoit Dherin Michael Munn Hanna Mazzawi Michael Wunder J. Gonzalvo ReLM OffRL LRM 490 14 0 24 Dec 2025
EvoEdit: Lifelong Free-Text Knowledge Editing through Latent Perturbation Augmentation and Knowledge-driven Parameter Fusion Pengfei Cao Zeao Ji Daojian Zeng Jun Zhao Kang Liu KELM 280 0 0 04 Dec 2025
Basis-Oriented Low-rank Transfer for Few-Shot and Test-Time Adaptation Junghwan Park Woojin Cho J. Heo Darongsae Kwon Kookjin Lee 48 0 0 02 Dec 2025
Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging Kuangpu Guo Yuhe Ding Jian Liang Zilei Wang Ran He MoMe 117 0 0 01 Dec 2025
From Coefficients to Directions: Rethinking Model Merging with Directional Alignment Zhikang Chen Sen Cui Deheng Ye Min Zhang Gang Niu Yu Zhang Masashi Sugiyama Tingting Zhu MoMe 147 0 0 29 Nov 2025
Mortgage Language Model: Domain-Adaptive Pretraining with Residual Instruction, Alignment Tuning, and Task-Specific Routing Manish Jain Satheesh Kumar Ponnambalam Salman Faroz Chandrakanth Lns Vinay Sharma ALM 615 0 0 26 Nov 2025
A Systematic Study of Model Merging Techniques in Large Language Models Oğuz Kağan Hitit Leander Girrbach Zeynep Akata MoMe 289 0 0 26 Nov 2025
Towards Benign Memory Forgetting for Selective Multimodal Large Language Model Unlearning Zhen Zeng Leijiang Gu Zhangling Duan Feng-Qiang Li Zenglin Shi Cees G. M. Snoek Meng Wang KELM MU CLL 246 0 0 25 Nov 2025
MergeVLA: Cross-Skill Model Merging Toward a Generalist Vision-Language-Action Agent Yuxia Fu Zhizhen Zhang Y. Zhang Zijian Wang Zi-Rui Huang Yadan Luo MoMe 265 0 0 24 Nov 2025
Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport Z. Pan Zhikang Chen Ding Li Min Zhang Sen Cui ... Yi Yang Deheng Ye Yu Zhang T. Zhu Tianling Ren MoMe CLL FedML 303 0 0 24 Nov 2025
Understanding and Mitigating Over-refusal for Large Language Models via Safety Representation Junbo Zhang Ran Chen Qianli Zhou Xinyang Deng Wen Jiang 169 1 0 24 Nov 2025
Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic Mostafa Mozafari F. Wani Maria Sofia Bucarelli Fabrizio Silvestri 124 0 0 24 Nov 2025
MergeSlide: Continual Model Merging and Task-to-Class Prompt-Aligned Inference for Lifelong Learning on Whole Slide Images Doanh C. Bui Ba-Hung Ngo H. Pham Khang Phuoc-Quy Nguyen Maï K. Nguyen Y. Nakashima CLL MoMe VLM 282 0 0 17 Nov 2025
Defending Unauthorized Model Merging via Dual-Stage Weight Protection Wei-Jia Chen Min-Yen Tsai Cheng-Yi Lee Chia-Mu Yu MoMe AAML 393 0 0 14 Nov 2025
Forgetting-MarI: LLM Unlearning via Marginal Information Regularization Shizhou Xu Yuan Ni Stefan Broecker Thomas Strohmer MU 315 0 0 14 Nov 2025
Radiology Workflow-Guided Hierarchical Reinforcement Fine-Tuning for Medical Report Generation Bodong Du Honglong Yang Xiaomeng Li 188 6 0 13 Nov 2025
Continual Unlearning for Text-to-Image Diffusion Models: A Regularization Perspective Justin Lee Zheda Mai Jinsu Yoo Chongyu Fan Cheng Zhang Wei-Lun Chao DiffM VLM 181 0 0 11 Nov 2025
You Had One Job: Per-Task Quantization Using LLMs' Hidden Representations Amit Levi Raz Lapid Rom Himelstein Yaniv Nemcovsky Ravid Shwartz Ziv A. Mendelson MQ 113 1 0 09 Nov 2025
DRAGON: Guard LLM Unlearning in Context via Negative Detection and ReasoningConference on Empirical Methods in Natural Language Processing (EMNLP), 2025 Y. Wang Chris Yuhao Liu Quan Liu Jinglong Pang Wei Wei Yujia Bao Yang Liu MU 323 1 0 08 Nov 2025
Steering Language Models with Weight Arithmetic Constanza Fierro Fabien Roger MoMe LLMSV 485 0 0 07 Nov 2025
Model Merging Improves Zero-Shot Generalization in Bioacoustic Foundation Models Davide Marincione Donato Crisostomi Roberto Dessi Emanuele Rodolà Emanuele Rossi MoMe AI4CE VLM 327 1 0 07 Nov 2025
Shared Parameter Subspaces and Cross-Task Linearity in Emergently Misaligned Behavior Daniel Aarao Reis Arturi Eric Zhang Andrew Ansah Kevin Zhu Ashwinee Panda Aishwarya Balwani 81 0 0 03 Nov 2025
T3: Test-Time Model Merging in VLMs for Zero-Shot Medical Imaging Analysis Raza Imam Hu Wang Dwarikanath Mahapatra Mohammad Yaqub MoMe 284 0 0 31 Oct 2025
Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP Yuxin Pan Zhiguang Cao Chengyang Gu Liu Liu Peilin Zhao Yize Chen Fangzhen Lin 185 0 0 24 Oct 2025
Model Merging with Functional Dual Anchors Kexuan Shi Yandong Wen Weiyang Liu MoMe 267 0 0 24 Oct 2025
PLAN: Proactive Low-Rank Allocation for Continual Learning Xiequn Wang Zhan Zhuang Yu Zhang CLL VLM 178 0 0 24 Oct 2025
Continual Knowledge Adaptation for Reinforcement Learning Jinwu Hu Zihao Lian Z. Wen Chenghao Li Guohao Chen Xutao Wen Bin Xiao Mingkui Tan CLL KELM 176 1 0 22 Oct 2025
Reasoning Distillation and Structural Alignment for Improved Code Generation Amir Jalilifard Anderson de Rezende Rocha Marcos Medeiros Raimundo OffRL LRM 108 0 0 20 Oct 2025
HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery Vaibhav Rathore Divyam Gupta Biplab Banerjee 123 0 0 20 Oct 2025
Forgetting to Forget: Attention Sink as A Gateway for Backdooring LLM Unlearning Bingqi Shang Yiwei Chen Yihua Zhang Bingquan Shen Sijia Liu MU KELM AAML 216 0 0 19 Oct 2025
MIN-Merging: Merge the Important Neurons for Model Merging Yunfei Liang MoMe 501 0 0 18 Oct 2025
Purifying Task Vectors in Knowledge-Aware Subspace for Model Merging Bang An Yibo Yang Philip Torr Bernard Ghanem MoMe 170 0 0 16 Oct 2025
Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch? Yijie Hu Zihao Zhou Kaizhu Huang Xiaowei Huang Qiufeng Wang LRM 118 1 0 16 Oct 2025
Directional Reasoning Injection for Fine-Tuning MLLMs Chao Huang Zeliang Zhang Jiang Liu Ximeng Sun Jialian Wu X. Yu Ze Wang Chenliang Xu Emad Barsoum Zicheng Liu MoMe LRM 196 1 0 16 Oct 2025
Backdoor Unlearning by Linear Task Decomposition Amel Abdelraheem Alessandro Favero Gérôme Bovet Pascal Frossard AAML MU 187 0 0 16 Oct 2025
REAP the Experts: Why Pruning Prevails for One-Shot MoE compression Mike Lasby Ivan Lazarevich Nish Sinnadurai Sean Lie Yani Andrew Ioannou Vithursan Thangarasa 108 1 0 15 Oct 2025
Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity Riccardo Santi Riccardo Salami Simone Calderara MU 148 0 0 15 Oct 2025
Weight Weaving: Parameter Pooling for Data-Free Model Merging Levy G. Chaves Eduardo Valle Sandra Avila MoMe 179 0 0 15 Oct 2025
Towards Reversible Model Merging For Low-rank Weights Mohammadsajad Alipour Mohammad Mohammadi Amiri MoMe 137 0 0 15 Oct 2025
Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice Kevin Kuo Chhavi Yadav Virginia Smith FedML 156 0 0 14 Oct 2025
Exploring and Leveraging Class Vectors for Classifier Editing Jaeik Kim Jaeyoung Do VLM 178 0 0 13 Oct 2025
Enhancing Faithfulness in Abstractive Summarization via Span-Level Fine-Tuning Sicong Huang Qianqi Yan Shengze Wang Ian Lane HILM 153 0 0 10 Oct 2025
Towards Efficient Multimodal Unified Reasoning Model via Model Merging Qixiang Yin Huanjin Yao Jianghao Chen Jiaxing Huang Z. Zhao Fei Su LRM MoMe 267 1 0 10 Oct 2025
Transmuting prompts into weights Hanna Mazzawi Benoit Dherin Michael Munn Michael Wunder Javier Gonzalvo LM&Ro 148 0 0 09 Oct 2025
Backdoor Vectors: a Task Arithmetic View on Backdoor Attacks and Defenses Stanisław Pawlak Jan Dubiñski Daniel Marczak Bartłomiej Twardowski AAML MoMe 224 0 0 09 Oct 2025
FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning Yunbo Li Jiaping Gui Zhihang Deng Fanchao Meng Yue Wu FedML 347 2 0 09 Oct 2025
Validation of Various Normalization Methods for Brain Tumor Segmentation: Can Federated Learning Overcome This Heterogeneity? Jan Fiszer Dominika Ciupek Maciej Malawski FedML 196 1 0 08 Oct 2025
Gradient-Sign Masking for Task Vector Transport Across Pre-Trained Models Filippo Rinaldi Aniello Panariello Giacomo Salici Fengyuan Liu Marco Ciccone Angelo Porrello Simone Calderara 167 0 0 07 Oct 2025
VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization Xinye Cao Hongcan Guo Jiawen Qian Guoshun Nan Chao Wang Yuqi Pan Tianhao Hou X. Wang Yutong Gao VGen 136 0 0 07 Oct 2025
Boomerang Distillation Enables Zero-Shot Model Size Interpolation Sara Kangaslahti Nihal V. Nayak Jonathan Geuter Marco Fumero Francesco Locatello David Alvarez-Melis 140 0 0 06 Oct 2025

All Papers

Editing Models with Task Arithmetic

Papers citing "Editing Models with Task Arithmetic"