Task Vector Merging

Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 24

All topics
CardsList

  1. A Broader Look at Model Merging: Rethinking Implicit Regularization Induced by Task Arithmetic

    Oct 6, 2026Sin-Han Yang, Shih-Cheng Huang, Chieh-Yen Lin +3Task Vector MergingMulti-Task Optimization

    Appier AI Research · National Taiwan University

  2. ChainLoRA: Geometry-Preserving Task Vector Merging for Continual Learning in LLMs

    Sep 30, 2026Hang Yin, Haozhe Wang, Yuhua Luo +3Continual Learning for LLMsLow-Rank Adaptation

    Shanghai Jiao Tong University · Shanghai Innovation Institute · Beijing Zhongguancun Academy +3

  3. No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy Distillation

    Sep 30, 2026Jingang Zhou, Feiyu Han, Han Zhu +6Task VectorsTask Vector Merging

    Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Ant Group

  4. Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging

    Sep 29, 2026Zijing Wang, Yongkang Liu, Mingyang Wang +8Task Vector MergingModel Merging

    Northeastern University, China · CIS, LMU Munich, Germany · Munich Center for Machine Learning (MCML), Germany +1

  5. CASS: Contribution-Aware Structured Sparsity for Model Merging

    Sep 28, 2026Yan Li, Guiping Cao, Meng Xu +5Multi-Task LearningStructured Sparsity

    Pengcheng Laboratory, Shenzhen, China · City University of Hong Kong, Hong Kong, China · Southern University of Science and Technology, Shenzhen, China +2

  6. Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging

    Sep 21, 2026Hyunjoong Cho, Jinhyeok JangMulti-Task LearningTask Vector Merging

    LG CNS · ETRI · UST

  7. Reading the Gate, Not the Interference: Output-Side Interference Measurement Does Not Track Merge Collapse

    Aug 12, 2026Chencheng ZhuTask Vector MergingTask Arithmetic

    UNSW Sydney

  8. HyperFix: Combinatorial Nonlinear Correction for Task Vector Merging

    Aug 11, 2026Hyo Seo Kim, Ren WangTask Vector MergingModel Merging

    Illinois Institute of Technology

  9. Signature-Guided Capacity Occupancy for Dense Expert Merging

    Aug 10, 2026Lingching Tung, Chi-Jui Kim, Beicheng Xu +2Task Vector MergingLanguage Model Merging

    Peking University · Independent Researcher

  10. Asymmetric Collapse in Model Merging: When Refusal Over- writes Recognition

    Jul 26, 2026Aarnav Choudhary, Matheus Fonseca Rocha, Jiwon Seo +2Language Model Safety EvaluationTask Vector Merging

    UCLA · Algoverse · Purdue University +1

  11. When Model Merging Rivals Joint Multi-Task Reinforcement Learning: A Task-Vector Geometry Analysis

    Jul 17, 2026S. Aaron McClendonTask Vector MergingMulti-Task RL

    Aimpoint Digital Labs

  12. DeltaMerge-LowRes: Composing Language and Task Deltas for Low-Resource Adaptation

    Jul 15, 2026Son Ha Xuan, Xuan-Bach Le, Phat T. Tran-TruongMultilingual Language ModelsTask Vector Merging

    RMIT University, Ho Chi Minh City, Vietnam · Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Ho Chi Minh City, Vietnam

  13. Training-free Task Classification for Multi-Task Model Merging

    Jun 21, 2026Jungyong Son, Jinwook Jung, Sungyong BaikMulti-Task LearningTask Vector Merging

    Department of Artificial Intelligence Hanyang University · Department of Data Science Hanyang University

  14. PACT: Preserving Anchored Cores in Task-vectors for Model Merging

    Jun 17, 2026Ningyuan Shi, Zhipeng Zhou, Hao Wang +2Multi-Task LearningTask Vector Merging

    Shanghai Jiao Tong University · Nanyang Technological University · The Hong Kong University of Science and Technology (Guangzhou)

  15. StereoFactory: A Unified Merging Framework for Robust Stereo Matching

    Jun 16, 2026Xianda Guo, Pinhan Fu, Ruilin Wang +3Stereo MatchingTask Vector Merging

    School of Computer Science, Wuhan University, Wuhan, China · D-Star Robotics, Beijing, China · Institute of Automation, Chinese Academy of Sciences, Beijing, China +1

  16. Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding

    Jun 8, 2026Shiyu Li, Zhiyuan Hu, Yifan Wang +3Multimodal EmbeddingCross-Modal Retrieval

    Tencent

  17. RogueMerge: Robust and Unified Attacks against LLM Model Merging

    Jun 2, 2026Jinghuai Zhang, Yetian He, Kunlin Cai +3LLM SecurityTask Vector Merging

    University of California, Los Angeles · University of Illinois Urbana-Champaign · University of Tennessee, Knoxville

  18. ResMerge: Residual-based Spectral Merging of Large Language Models

    Jun 1, 2026Yandu Sun, Zhiyan Hou, Haokai Ma +6Task Vector MergingLanguage Model Merging

    1Southeast University, Nanjing, China · Institute of Automation, Chinese Academy of Sciences · University of Chinese Academy of Sciences +4

  19. Saliency-Aware Model Merging

    May 30, 2026Jungin Park, Jiyoung Lee, Kwanghoon SohnTask Vector MergingModel Merging

    Yonsei University, Seoul, South Korea · Ewha Womans University, Seoul, South Korea.

  20. Model Merging on Loss Landscape: A Geometry Perspective

    May 26, 2026Juanwu Lu, Anand Bhaskar, Brian Axelrod +2Task Vector MergingModel Merging

    Purdue University · Waymo LLC

  21. Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey

    May 13, 2026Kunil Lee, Ki-Young Shin, Jong-Hyeok Lee +1Knowledge EditingMultilingual Language Models

    Department of Computer Science and Engineering, POSTECH · Designovel Co., Ltd. · LLSOLLU +1

  22. Model Merging: Foundations and Algorithms

    May 2, 2026Donato CrisostomiMulti-Task LearningTask Vector Merging

    SAPIENZA UNIVERSITY OF ROME · GLADIA research lab · Department of Computer Science +1

  23. Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression

    Apr 30, 2026Junqi Gao, Dazhi Zhang, Zhichang Guo +3Task VectorsTask Vector Merging

    School of Mathematics, Harbin Institute of Technology, Harbin, P. R. China · Shanghai Artificial Intelligence Laboratory, Shanghai, P. R. China

  24. Crowded in B-Space: Calibrating Shared Directions for LoRA Merging

    Apr 18, 2026Yixuan Tang, Yi YangAdapter TuningLow-Rank Adaptation

    The Hong Kong University of Science and Technology