Imagen de Portada

MergeBench: A Benchmark for Merging Domain-Specialized LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	He, Yifei, Zeng, Siqi, Hu, Yuzheng, Yang, Rui, Zhang, Tong, Zhao, Han
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Channel Merging: Preserving Specialization for Merged Experts
por: Zhang, Mingyang, et al.
Publicado: (2024)

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

Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
por: Tang, Anke, et al.
Publicado: (2025)

MergeMoE: Efficient Compression of MoE Models via Expert Output Merging
por: Miao, Ruijie, et al.
Publicado: (2025)

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

PSO-Merging: Merging Models Based on Particle Swarm Optimization
por: Zhang, Kehao, et al.
Publicado: (2025)

Merging Smarter, Generalizing Better: Enhancing Model Merging on OOD Data
por: Zhang, Bingjie, et al.
Publicado: (2025)

BadMerging: Backdoor Attacks Against Model Merging
por: Zhang, Jinghuai, et al.
Publicado: (2024)

Merge-Bench: Resolve Merge Conflicts with Large Language Models
por: Schesch, Benedikt, et al.
Publicado: (2026)

MIN-Merging: Merge the Important Neurons for Model Merging
por: Liang, Yunfei
Publicado: (2025)

FedMerge: Federated Personalization via Model Merging
por: Chen, Shutong, et al.
Publicado: (2025)

NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
por: Kim, Hyo Seo, et al.
Publicado: (2024)

MergeIT: From Selection to Merging for Efficient Instruction Tuning
por: Cai, Hongyi, et al.
Publicado: (2025)

Mitigating Training Imbalance in LLM Fine-Tuning via Selective Parameter Merging
por: Ju, Yiming, et al.
Publicado: (2024)

Expert Merging: Model Merging with Unsupervised Expert Alignment and Importance-Guided Layer Chunking
por: Zhang, Dengming, et al.
Publicado: (2025)

SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
por: Jung, Aecheon, et al.
Publicado: (2024)

Orthogonal Model Merging
por: Yang, Sihan, et al.
Publicado: (2026)

FW-Merging: Scaling Model Merging with Frank-Wolfe Optimization
por: Chen, Hao Mark, et al.
Publicado: (2025)

Bayesian Model Merging
por: Li, Kaiyang, et al.
Publicado: (2026)

Rethinking Layer-wise Model Merging through Chain of Merges
por: Buzzega, Pietro, et al.
Publicado: (2025)

Merge and Guide: Unifying Model Merging and Guided Decoding for Controllable Multi-Objective Generation
por: Xie, Guofu, et al.
Publicado: (2025)

Merge-of-Thought Distillation
por: Shen, Zhanming, et al.
Publicado: (2025)

MergeMix: Optimizing Mid-Training Data Mixtures via Learnable Model Merging
por: Wang, Jiapeng, et al.
Publicado: (2026)

Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
por: Chen, Weiyu, et al.
Publicado: (2024)

Surrogate Benchmarks for Model Merging Optimization
por: Akizuki, Rio, et al.
Publicado: (2025)

MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
por: Dong, Zilu, et al.
Publicado: (2025)

Extra-Merge: Tracing the Rank-1 Subspace of Model Merging in Language Model Pre-Training
por: Zhou, Wenjie, et al.
Publicado: (2026)

A Hybrid Framework for Spatial Interpolation: Merging Data-driven with Domain Knowledge
por: Zhang, Cong, et al.
Publicado: (2024)

AdaMerging: Adaptive Model Merging for Multi-Task Learning
por: Yang, Enneng, et al.
Publicado: (2023)

Merge Now, Regret Later: The Hidden Cost of Model Merging is Adversarial Transferability
por: Gangwal, Ankit, et al.
Publicado: (2025)

CavMerge: Merging K-means Based on Local Log-Concavity
por: Qiao, Zhili, et al.
Publicado: (2026)

Merge before Forget: A Single LoRA Continual Learning via Continual Merging
por: Qiao, Fuli, et al.
Publicado: (2025)

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging
por: Li, Lujun, et al.
Publicado: (2025)

CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
por: Sun, Wenju, et al.
Publicado: (2025)

REAM: Merging Improves Pruning of Experts in LLMs
por: Jha, Saurav, et al.
Publicado: (2026)

MergeDNA: Context-aware Genome Modeling with Dynamic Tokenization through Token Merging
por: Li, Siyuan, et al.
Publicado: (2025)

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

Training-free Heterogeneous Model Merging
por: Xu, Zhengqi, et al.
Publicado: (2024)

Parameter Competition Balancing for Model Merging
por: Du, Guodong, et al.
Publicado: (2024)