Imagen de Portada

Decentralized Instruction Tuning: Conflict-Aware Splitting and Weight Merging

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Choi, Minsik, Kim, Geewook
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Revisiting Weight Averaging for Model Merging
por: Choi, Jiho, et al.
Publicado: (2024)

MAny: Merge Anything for Multimodal Continual Instruction Tuning
por: Gao, Zijian, et al.
Publicado: (2026)

Parameter-Efficient Checkpoint Merging via Metrics-Weighted Averaging
por: Yu, Shi Jie, et al.
Publicado: (2025)

CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging
por: Yang, Zongzhen, et al.
Publicado: (2025)

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

Entropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
por: Choi, Minsik, et al.
Publicado: (2025)

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

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
por: Hui, Tingfeng, et al.
Publicado: (2024)

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

Stable Trajectory Clustering: An Efficient Split and Merge Algorithm
por: Rahmani, Atieh, et al.
Publicado: (2025)

Mitigating Parameter Interference in Model Merging via Sharpness-Aware Fine-Tuning
por: Lee, Yeoreum, et al.
Publicado: (2025)

XFT: Unlocking the Power of Code Instruction Tuning by Simply Merging Upcycled Mixture-of-Experts
por: Ding, Yifeng, et al.
Publicado: (2024)

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

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

Merge and Bound: Direct Manipulations on Weights for Class Incremental Learning
por: Kim, Taehoon, et al.
Publicado: (2025)

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

On Transferring, Merging, and Splitting Task-Oriented Network Digital Twins
por: Zhang, Zifan, et al.
Publicado: (2025)

Dataless Knowledge Fusion by Merging Weights of Language Models
por: Jin, Xisen, et al.
Publicado: (2022)

Text2Chart31: Instruction Tuning for Chart Generation with Automatic Feedback
por: Zadeh, Fatemeh Pesaran, et al.
Publicado: (2024)

Bridging Training and Merging Through Momentum-Aware Optimization
por: Moayedikia, Alireza, et al.
Publicado: (2025)

Sparsity-Aware Evolution for Model Merging
por: Zhang, Huan, et al.
Publicado: (2026)

OLC-WA: Drift Aware Tuning-Free Online Classification with Weighted Average
por: Shaira, Mohammad Abu, et al.
Publicado: (2025)

Real-Time Conflict Prediction for Large Truck Merging in Mixed Traffic at Work Zone Lane Closures
por: Enan, Abyad, et al.
Publicado: (2025)

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation
por: Liao, Yunming, et al.
Publicado: (2023)

D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
por: Zhang, Jia, et al.
Publicado: (2025)

Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
por: Lee, Hyungu, et al.
Publicado: (2025)

Stabilizing Decentralized Federated Fine-Tuning via Topology-Aware Alternating LoRA
por: Wang, Xiaoyu, et al.
Publicado: (2026)

Decentralized Low-Rank Fine-Tuning of Large Language Models
por: Ghiasvand, Sajjad, et al.
Publicado: (2025)

Conflict-Aware Adversarial Training
por: Xue, Zhiyu, et al.
Publicado: (2024)

HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric
por: Penedo, Carlos Beis, et al.
Publicado: (2025)

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

Who is In Charge? Dissecting Role Conflicts in Instruction Following
por: Zeng, Siqi
Publicado: (2025)

BD-Merging: Bias-Aware Dynamic Model Merging with Evidence-Guided Contrastive Learning
por: Xie, Yuhan, et al.
Publicado: (2026)

Uncertainty-Aware Gradient Signal-to-Noise Data Selection for Instruction Tuning
por: Yuan, Zhihang, et al.
Publicado: (2026)

Diversity Measurement and Subset Selection for Instruction Tuning Datasets
por: Wang, Peiqi, et al.
Publicado: (2024)

Tracking Universal Features Through Fine-Tuning and Model Merging
por: Horn, Niels, et al.
Publicado: (2024)

Diffusion Instruction Tuning
por: Jin, Chen, et al.
Publicado: (2025)

On the Surprising Effectiveness of a Single Global Merging in Decentralized Learning
por: Zhu, Tongtian, et al.
Publicado: (2025)

DIMAT: Decentralized Iterative Merging-And-Training for Deep Learning Models
por: Saadati, Nastaran, et al.
Publicado: (2024)