Imagen de Portada

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Enneng, Wang, Zhenyi, Shen, Li, Liu, Shiwei, Guo, Guibing, Wang, Xingwei, Tao, Dacheng
Formato:	Preprint
Publicado:	2023
Materias:	Machine Learning Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Representation Surgery for Multi-Task Model Merging
por: Yang, Enneng, et al.
Publicado: (2024)

SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
por: Yang, Enneng, et al.
Publicado: (2024)

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
por: Yang, Enneng, et al.
Publicado: (2024)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
por: Shen, Li, et al.
Publicado: (2024)

AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
por: Yang, Enneng, et al.
Publicado: (2022)

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
por: Tang, Anke, et al.
Publicado: (2024)

Multi-Task Model Merging via Adaptive Weight Disentanglement
por: Xiong, Feng, et al.
Publicado: (2024)

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning
por: Wang, Zhenyi, et al.
Publicado: (2023)

AdaRank: Adaptive Rank Pruning for Enhanced Model Merging
por: Lee, Chanhyuk, et al.
Publicado: (2025)

Stay Unique, Stay Efficient: Preserving Model Personality in Multi-Task Merging
por: Guo, Kuangpu, et al.
Publicado: (2025)

Continual Learning From a Stream of APIs
por: Yang, Enneng, et al.
Publicado: (2023)

Localizing Task Information for Improved Model Merging and Compression
por: Wang, Ke, et al.
Publicado: (2024)

EMR-Merging: Tuning-Free High-Performance Model Merging
por: Huang, Chenyu, et al.
Publicado: (2024)

Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning
por: Hu, Zixuan, et al.
Publicado: (2023)

MedMerge: Merging Models for Effective Transfer Learning to Medical Imaging Tasks
por: Almakky, Ibrahim, et al.
Publicado: (2024)

FREE: Faster and Better Data-Free Meta-Learning
por: Wei, Yongxian, et al.
Publicado: (2024)

DC-Merge: Improving Model Merging with Directional Consistency
por: Zhang, Han-Chen, et al.
Publicado: (2026)

Learning to Learn from APIs: Black-Box Data-Free Meta-Learning
por: Hu, Zixuan, et al.
Publicado: (2023)

Efficient Visual Transformer by Learnable Token Merging
por: Wang, Yancheng, et al.
Publicado: (2024)

ZipIt! Merging Models from Different Tasks without Training
por: Stoica, George, et al.
Publicado: (2023)

Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
por: Wang, Xi, et al.
Publicado: (2026)

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
por: Yang, Huitong, et al.
Publicado: (2025)

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
por: Zeng, Fanhu, et al.
Publicado: (2025)

Efficient Multi-Source Knowledge Transfer by Model Merging
por: Osial, Marcin, et al.
Publicado: (2025)

Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
por: Ma, Qianli, et al.
Publicado: (2024)

ATM: Improving Model Merging by Alternating Tuning and Merging
por: Zhou, Luca, et al.
Publicado: (2024)

Saliency-Aware Model Merging
por: Park, Jungin, et al.
Publicado: (2026)

FREE-Merging: Fourier Transform for Efficient Model Merging
por: Zheng, Shenghe, et al.
Publicado: (2024)

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
por: Du, Yiyang, et al.
Publicado: (2025)

Merging without Forgetting: Continual Fusion of Task-Specific Models via Optimal Transport
por: Pan, Zecheng, et al.
Publicado: (2025)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
por: Gong, Wenyi, et al.
Publicado: (2025)

LARV: Data-Free Layer-wise Adaptive Rescaling Veneer for Model Merging
por: Wang, Xinyu, et al.
Publicado: (2026)

From Parameter to Representation: A Closed-Form Approach for Controllable Model Merging
por: Wu, Jialin, et al.
Publicado: (2025)

Decouple and Orthogonalize: A Data-Free Framework for LoRA Merging
por: Zheng, Shenghe, et al.
Publicado: (2025)

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
por: Huang, Chenyu, et al.
Publicado: (2026)

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
por: Kim, Jinuk, et al.
Publicado: (2024)

Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications
por: Hu, Zixuan, et al.
Publicado: (2025)

RegCL: Continual Adaptation of Segment Anything Model via Model Merging
por: Shu, Yuan-Chen, et al.
Publicado: (2025)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
por: He, Yifei, et al.
Publicado: (2024)

Single-Input Multi-Output Model Merging: Leveraging Foundation Models for Dense Multi-Task Learning
por: Giraldo, Juan Garcia, et al.
Publicado: (2025)