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
How does the optimizer implicitly bias the model merging loss landscape? Chenxiang Zhang Alexander Theus Damien Teney Antonio Orvieto Jun Pang S. Mauw MoMe 178 1 0 06 Oct 2025
Learning to Interpret Weight Differences in Language Models Avichal Goel Yoon Kim Nir Shavit T. T. Wang 175 1 0 06 Oct 2025
MLLMEraser: Achieving Test-Time Unlearning in Multimodal Large Language Models through Activation Steering Chenlu Ding Jiancan Wu Leheng Sheng Fan Zhang Yancheng Yuan Xiang Wang Xiangnan He MU KELM 235 0 0 05 Oct 2025
Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking Dengming Zhang Xiaowen Ma Zhenliang Ni Zhenkai Wu Han Shu Xin Jiang Xinghao Chen MoMe 144 2 0 30 Sep 2025
BiasFreeBench: a Benchmark for Mitigating Bias in Large Language Model Responses Xin Xu Xunzhi He Churan Zhi Ruizhe Chen Julian McAuley Zexue He 90 0 0 30 Sep 2025
Real-Aware Residual Model Merging for Deepfake Detection Jinhee Park Guisik Kim Choongsang Cho Junseok Kwon MoMe 136 0 0 29 Sep 2025
Understanding the Dilemma of Unlearning for Large Language Models Qingjie Zhang Haoting Qian Zhicong Huang Cheng Hong Shiyu Huang Ke Xu Chao Zhang Han Qiu MU 232 1 0 29 Sep 2025
Model Merging Scaling Laws in Large Language Models Yuanyi Wang Yanggan Gu Yiming Zhang Qi Zhou Zhaoyi Yan C. Xie X. Wang Jianbo Yuan Hongxia Yang MoMe 302 1 0 29 Sep 2025
TDHook: A Lightweight Framework for Interpretability Yoann Poupart AI4CE 108 0 0 29 Sep 2025
Stable Forgetting: Bounded Parameter-Efficient Unlearning in LLMs Arpit Garg Hemanth Saratchandran Ravi Garg Simon Lucey MU CLL 113 1 0 29 Sep 2025
Bridging the Knowledge-Prediction Gap in LLMs on Multiple-Choice Questions Yoonah Park Haesung Pyun Yohan Jo KELM 323 0 0 28 Sep 2025
Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability Ankit Gangwal Aaryan Ajay Sharma AAML MoMe 169 1 0 28 Sep 2025
Toward a Holistic Approach to Continual Model Merging Hoang Phan Sungmin Cha Tung Lam Tran Qi Lei MoMe CLL 182 1 0 28 Sep 2025
Guard Vector: Beyond English LLM Guardrails with Task-Vector Composition and Streaming-Aware Prefix SFT Wonhyuk Lee Youngchol Kim Yunjin Park Junhyung Moon Dongyoung Jeong Wanjin Park 124 0 0 27 Sep 2025
Dual-Space Smoothness for Robust and Balanced LLM Unlearning Han Yan Zheyuan Liu Meng Jiang MU AAML 108 0 0 27 Sep 2025
Temporal Generalization: A Reality Check Divyam Madaan S. Chopra Kyunghyun Cho OOD AI4TS 116 0 0 27 Sep 2025
The Thinking Spectrum: An Empirical Study of Tunable Reasoning in LLMs through Model Merging Xiaochong Lan Yu Zheng Shiteng Cao Yong Li MoMe LRM 203 0 0 26 Sep 2025
Context Parametrization with Compositional Adapters Josip Jukić Martin Tutek Jan Snajder 116 0 0 26 Sep 2025
Closing the Oracle Gap: Increment Vector Transformation for Class Incremental Learning Zihuan Qiu Yi Xu Fanman Meng Runtong Zhang Linfeng XU Qingbo Wu Hongliang Li CLL VLM 137 0 0 26 Sep 2025
SFT Doesn't Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMs J. Lin Zhongruo Wang Kun Qian Tian Wang Arvind Srinivasan ... Weiqi Zhang Sujay Sanghavi C. L. P. Chen Hyokun Yun Lihong Li CLL 326 1 0 25 Sep 2025
Null-Space Filtering for Data-Free Continual Model Merging: Preserving Transparency, Promoting Fidelity Zihuan Qiu Lei Wang Yang Cao Runtong Zhang Bing Su Yi Xu Fanman Meng Linfeng XU Qingbo Wu Hongliang Li 117 0 0 25 Sep 2025
Faster, Smaller, and Smarter: Task-Aware Expert Merging for Online MoE Inference Ziyi Han Xutong Liu Ruiting Zhou Xiangxiang Dai J. C. Lui MoMe MoE 137 0 0 24 Sep 2025
LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions Xixun Lin Yucheng Ning Jingwen Zhang Yan Dong Y. Liu ... Bin Wang Yanan Cao Kai-xiang Chen Songlin Hu Li Guo LLMAG LRM 298 4 0 23 Sep 2025
SEQR: Secure and Efficient QR-based LoRA Routing William Fleshman Benjamin Van Durme 156 0 0 22 Sep 2025
Accurate and Efficient Low-Rank Model Merging in Core Space Aniello Panariello Daniel Marczak Simone Magistri Angelo Porrello Bartłomiej Twardowski Andrew D. Bagdanov Simone Calderara Joost van de Weijer MoMe 244 2 0 22 Sep 2025
Variational Task Vector Composition Boyuan Zhang Yingjun Du Xiantong Zhen Ling Shao MoMe CoGe 174 0 0 21 Sep 2025
Local Mechanisms of Compositional Generalization in Conditional Diffusion Arwen Bradley DiffM CoGe 221 1 0 19 Sep 2025
HAM: Hierarchical Adapter Merging for Scalable Continual Learning Eric Nuertey Coleman Luigi Quarantiello Samrat Mukherjee J. Hurtado Vincenzo Lomonaco CLL MoMe 300 1 0 16 Sep 2025
Programmable Cognitive Bias in Social Agents Xuan Liu HaoYang Shang Haojian Jin 158 1 0 16 Sep 2025
Harnessing Optimization Dynamics for Curvature-Informed Model Merging Pouria Mahdavinia Hamed Mahdavi Niloofar Mireshghallah M. Mahdavi MoMe 167 1 0 14 Sep 2025
Continually Adding New Languages to Multilingual Language Models A. Owodunni Sachin Kumar CLL KELM MoMe 177 2 0 14 Sep 2025
Delta Activations: A Representation for Finetuned Large Language Models Zhiqiu Xu Amish Sethi Mayur Naik Ser-Nam Lim 138 0 0 04 Sep 2025
Unlearning That Lasts: Utility-Preserving, Robust, and Almost Irreversible Forgetting in LLMs Naman D. Singh Maximilian Müller Francesco Croce Matthias Hein MU KELM CLL 187 4 0 02 Sep 2025
Surrogate Benchmarks for Model Merging Optimization Rio Akizuki Yuya Kudo Nozomu Yoshinari Yoichi Hirose Toshiyuki Nishimoto Kento Uchida Shinichi Shirakawa MoMe 137 0 0 02 Sep 2025
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic Mohammad Zbeeb Hasan Hammoud Bernard Ghanem LRM 168 1 0 01 Sep 2025
Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing Zihao Wang Enneng Yang L. Yin Shiwei Liu Li Shen FedML MoMe 152 0 0 01 Sep 2025
Improving Fisher Information Estimation and Efficiency for LoRA-based LLM Unlearning Yejin Kim Eunwon Kim Buru Chang Junsuk Choe MU 115 1 0 29 Aug 2025
Rethinking Layer-wise Model Merging through Chain of Merges Pietro Buzzega Riccardo Salami Angelo Porrello Simone Calderara MoMe AI4CE 183 0 0 29 Aug 2025
Lethe: Purifying Backdoored Large Language Models with Knowledge Dilution Chen Chen Yuchen Sun Jiaxin Gao Xueluan Gong Qian-Wei Wang Ziyao Wang Yongsen Zheng K. Lam AAML KELM 140 0 0 28 Aug 2025
PSO-Merging: Merging Models Based on Particle Swarm Optimization Kehao Zhang Shaolei Zhang Yang Feng MoMe 111 0 0 27 Aug 2025
UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models Yimu Wang Weiming Zhuang Chen Chen Jiabo Huang Jingtao Li Lingjuan Lyu FedML 104 1 0 27 Aug 2025
AMELIA: A Family of Multi-task End-to-end Language Models for Argumentation Henri Savigny Bruno Yun LLMAG 70 0 0 25 Aug 2025
Modular Embedding Recomposition for Incremental Learning Aniello Panariello Emanuele Frascaroli Pietro Buzzega Lorenzo Bonicelli Angelo Porrello Simone Calderara VLM 171 2 0 22 Aug 2025
On Task Vectors and Gradients Luca Zhou Daniele Solombrino Donato Crisostomi Maria Sofia Bucarelli Giuseppe Alessio D’Inverno Fabrizio Silvestri Emanuele Rodolà MoMe 389 1 0 22 Aug 2025
Think in Blocks: Adaptive Reasoning from Direct Response to Deep Reasoning Yekun Zhu Guang Chen Chengjun Mao OffRL LRM AI4CE 65 0 0 21 Aug 2025
Learn Faster and Remember More: Balancing Exploration and Exploitation for Continual Test-time Adaptation Pinci Yang Peisong Wen Ke Ma Qianqian Xu CLL TTA 250 0 0 18 Aug 2025
Cost-Aware Contrastive Routing for LLMs Reza Shirkavand Shangqian Gao Qi He Heng-Chiao Huang 287 1 0 17 Aug 2025
Rethinking Safety in LLM Fine-tuning: An Optimization Perspective Minseon Kim Jin Myung Kwak Lama Alssum Bernard Ghanem Juil Sock David M. Krueger Fazl Barez Adel Bibi 127 2 0 17 Aug 2025
MedSAMix: A Training-Free Model Merging Approach for Medical Image Segmentation Yanwu Yang Guinan Su Jiesi Hu Francesco Sammarco Jonas Geiping Thomas Wolfers MedIm VLM 110 2 0 14 Aug 2025
VisCodex: Unified Multimodal Code Generation via Merging Vision and Coding Models Lingjie Jiang Shaohan Huang Xun Wu Yixia Li Dongdong Zhang Furu Wei MLLM VLM 159 3 0 13 Aug 2025