Image de couverture de livre

From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ruan, Wei, Yang, Tianze, Zhou, Yifan, Liu, Tianming, Lu, Jin
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces
par: Marczak, Daniel, et autres
Publié: (2025)

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
par: Zheng, Bowen, et autres
Publié: (2025)

ICE-SEARCH: A Language Model-Driven Feature Selection Approach
par: Yang, Tianze, et autres
Publié: (2024)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
par: Yang, Enneng, et autres
Publié: (2023)

Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
par: Tang, Anke, et autres
Publié: (2025)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
par: Pan, Zecheng, et autres
Publié: (2025)

Towards Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects
par: Zólyomi, Levente, et autres
Publié: (2025)

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
par: Wei, Yongxian, et autres
Publié: (2025)

Orthogonal Model Merging
par: Yang, Sihan, et autres
Publié: (2026)

Less is More: Efficient Model Merging with Binary Task Switch
par: Qi, Biqing, et autres
Publié: (2024)

Evaluating Mathematical Reasoning Across Large Language Models: A Fine-Grained Approach
par: Jahin, Afrar, et autres
Publié: (2025)

Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation
par: Xie, Guofu, et autres
Publié: (2025)

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
par: Zhou, Wenjie, et autres
Publié: (2026)

Task Vector Quantization for Memory-Efficient Model Merging
par: Kim, Youngeun, et autres
Publié: (2025)

Model Breadcrumbs: Scaling Multi-Task Model Merging with Sparse Masks
par: Davari, MohammadReza, et autres
Publié: (2023)

From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging
par: Wu, Jialin, et autres
Publié: (2025)

Superpose Task-specific Features for Model Merging
par: Qiu, Haiquan, et autres
Publié: (2025)

Merging by Matching Models in Task Parameter Subspaces
par: Tam, Derek, et autres
Publié: (2023)

FedMerge: Federated Personalization via Model Merging
par: Chen, Shutong, et autres
Publié: (2025)

Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
par: Lu, Zhenyi, et autres
Publié: (2024)

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
par: Sun, Wenju, et autres
Publié: (2025)

Task Arithmetic in Trust Region: A Training-Free Model Merging Approach to Navigate Knowledge Conflicts
par: Sun, Wenju, et autres
Publié: (2025)

Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging
par: Wang, Yuanyi, et autres
Publié: (2026)

MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
par: Li, Kunxi, et autres
Publié: (2024)

Representation Surgery for Multi-Task Model Merging
par: Yang, Enneng, et autres
Publié: (2024)

From Function to Distribution Modeling: A PAC-Generative Approach to Offline Optimization
par: Zhang, Qiang, et autres
Publié: (2024)

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
par: Cheng, Runxi, et autres
Publié: (2025)

Merging Language and Domain Specific Models: The Impact on Technical Vocabulary Acquisition
par: Rousset, Thibault, et autres
Publié: (2025)

Task Vector Bases: A Unified and Scalable Framework for Compressed Task Arithmetic
par: Zeng, Siqi, et autres
Publié: (2025)

Model Merging in Pre-training of Large Language Models
par: Li, Yunshui, et autres
Publié: (2025)

DC-Merge: Improving Model Merging with Directional Consistency
par: Zhang, Han-Chen, et autres
Publié: (2026)

Merge to Learn: Efficiently Adding Skills to Language Models with Model Merging
par: Morrison, Jacob, et autres
Publié: (2024)

Bi-level Personalization for Federated Foundation Models: A Task-vector Aggregation Approach
par: Yang, Yiyuan, et autres
Publié: (2025)

A Unified Generalization Framework for Model Merging: Trade-offs, Non-Linearity, and Scaling Laws
par: Li, Qinglun, et autres
Publié: (2026)

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
par: Yang, Jinluan, et autres
Publié: (2025)

Model Merging with Functional Dual Anchors
par: Shi, Kexuan, et autres
Publié: (2025)

PSO-Merging: Merging Models Based on Particle Swarm Optimization
par: Zhang, Kehao, et autres
Publié: (2025)

Localizing Task Information for Improved Model Merging and Compression
par: Wang, Ke, et autres
Publié: (2024)

SoFlow: Solution Flow Models for One-Step Generative Modeling
par: Luo, Tianze, et autres
Publié: (2025)

BadMerging: Backdoor Attacks Against Model Merging
par: Zhang, Jinghuai, et autres
Publié: (2024)