Image de couverture de livre

DC-Merge: Improving Model Merging with Directional Consistency

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhang, Han-Chen, Zhou, Zi-Hao, Luo, Mao-Lin, Di, Shimin, Zhang, Min-Ling, Wei, Tong
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving
par: Yang, Huitong, et autres
Publié: (2025)

LADA: Scalable Label-Specific CLIP Adapter for Continual Learning
par: Luo, Mao-Lin, et autres
Publié: (2025)

EMR-Merging: Tuning-Free High-Performance Model Merging
par: Huang, Chenyu, et autres
Publié: (2024)

ATM: Improving Model Merging by Alternating Tuning and Merging
par: Zhou, Luca, et autres
Publié: (2024)

KeepLoRA: Continual Learning with Residual Gradient Adaptation
par: Luo, Mao-Lin, et autres
Publié: (2026)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
par: He, Yifei, et autres
Publié: (2024)

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness
par: Zeng, Fanhu, et autres
Publié: (2025)

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

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

Merging Multi-Task Models via Weight-Ensembling Mixture of Experts
par: Tang, Anke, et autres
Publié: (2024)

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
par: Kim, Taehoon, et autres
Publié: (2025)

Saliency-Aware Model Merging
par: Park, Jungin, et autres
Publié: (2026)

RegCL: Continual Adaptation of Segment Anything Model via Model Merging
par: Shu, Yuan-Chen, et autres
Publié: (2025)

CubistMerge: Spatial-Preserving Token Merging For Diverse ViT Backbones
par: Gong, Wenyi, et autres
Publié: (2025)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
par: Shen, Li, et autres
Publié: (2024)

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
par: Kim, Jinuk, et autres
Publié: (2024)

Parameter Competition Balancing for Model Merging
par: Du, Guodong, et autres
Publié: (2024)

Transferring Textual Preferences to Vision-Language Understanding through Model Merging
par: Li, Chen-An, et autres
Publié: (2025)

Subspace-Boosted Model Merging
par: Skorobogat, Ronald, et autres
Publié: (2025)

Harmonizing and Merging Source Models for CLIP-based Domain Generalization
par: Ding, Yuhe, et autres
Publié: (2025)

Multi-Task Model Merging via Adaptive Weight Disentanglement
par: Xiong, Feng, et autres
Publié: (2024)

Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
par: Zhang, Yiming, et autres
Publié: (2024)

Efficient Multi-Source Knowledge Transfer by Model Merging
par: Osial, Marcin, et autres
Publié: (2025)

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

Bridging Domains through Subspace-Aware Model Merging
par: Chaves, Levy, et autres
Publié: (2026)

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

MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
par: Zhang, Luyuan, et autres
Publié: (2026)

Resolving Interference (RI): Disentangling Models for Improved Model Merging
par: Ramesh, Pratik, et autres
Publié: (2026)

FREE-Merging: Fourier Transform for Efficient Model Merging
par: Zheng, Shenghe, et autres
Publié: (2024)

ZipIt! Merging Models from Different Tasks without Training
par: Stoica, George, et autres
Publié: (2023)

Weight Weaving: Parameter Pooling for Data-Free Model Merging
par: Chaves, Levy, et autres
Publié: (2025)

Efficient Visual Transformer by Learnable Token Merging
par: Wang, Yancheng, et autres
Publié: (2024)

Realistic Evaluation of Model Merging for Compositional Generalization
par: Tam, Derek, et autres
Publié: (2024)

Exploring Model Kinship for Merging Large Language Models
par: Hu, Yedi, et autres
Publié: (2024)

SSAM: Singular Subspace Alignment for Merging Multimodal Large Language Models
par: Reza, Md Kaykobad, et autres
Publié: (2026)

Revitalizing the Beginning: Avoiding Storage Dependency for Model Merging in Continual Learning
par: Wang, Xi, et autres
Publié: (2026)

Sequential Token Merging: Revisiting Hidden States
par: Wen, Yan, et autres
Publié: (2025)

FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
par: Huang, Chenyu, et autres
Publié: (2026)

Unleashing the Power of Vision-Language Models for Long-Tailed Multi-Label Visual Recognition
par: Tang, Wei, et autres
Publié: (2025)

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding
par: Wang, Haoxiang, et autres
Publié: (2023)