Copertina

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cheng, Runxi, Xiong, Feng, Wei, Yongxian, Zhu, Wanyun, Yuan, Chun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Learn To Learn More Precisely
di: Cheng, Runxi, et al.
Pubblicazione: (2024)

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
di: Wei, Yongxian, et al.
Pubblicazione: (2025)

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
di: Wei, Yongxian, et al.
Pubblicazione: (2024)

Task-Distributionally Robust Data-Free Meta-Learning
di: Hu, Zixuan, et al.
Pubblicazione: (2023)

End-to-End Reaction Field Energy Modeling via Deep Learning based Voxel-to-voxel Transform
di: Wu, Yongxian, et al.
Pubblicazione: (2024)

Task Singular Vectors: Reducing Task Interference in Model Merging
di: Gargiulo, Antonio Andrea, et al.
Pubblicazione: (2024)

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

Task Vector Quantization for Memory-Efficient Model Merging
di: Kim, Youngeun, et al.
Pubblicazione: (2025)

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

Unlocking Tuning-Free Few-Shot Adaptability in Visual Foundation Models by Recycling Pre-Tuned LoRAs
di: Hu, Zixuan, et al.
Pubblicazione: (2024)

DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
di: Yoshida, Kotaro, et al.
Pubblicazione: (2025)

Model Merging via Data-Free Covariance Estimation
di: Hameed, Marawan Gamal Abdel, et al.
Pubblicazione: (2026)

Chorus: Harmonizing Context and Sensing Signals for Data-Free Model Customization in IoT
di: Zhang, Liyu, et al.
Pubblicazione: (2025)

Tensorized Clustered LoRA Merging for Multi-Task Interference
di: Su, Zhan, et al.
Pubblicazione: (2025)

OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
di: Wei, Yongxian, et al.
Pubblicazione: (2025)

MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model Training
di: Xie, Wanyun, et al.
Pubblicazione: (2026)

Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
di: Gao, Junqi, et al.
Pubblicazione: (2026)

Retraining-Free Merging of Sparse MoE via Hierarchical Clustering
di: Chen, I-Chun, et al.
Pubblicazione: (2024)

Janus-Q: End-to-End Event-Driven Trading via Hierarchical-Gated Reward Modeling
di: Li, Xiang, et al.
Pubblicazione: (2026)

HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocation
di: Xiong, Feng, et al.
Pubblicazione: (2025)

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

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler
di: Hu, Zixuan, et al.
Pubblicazione: (2025)

Chameleon: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning
di: Xie, Wanyun, et al.
Pubblicazione: (2025)

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

Guided Model Merging for Hybrid Data Learning: Leveraging Centralized Data to Refine Decentralized Models
di: Zhu, Junyi, et al.
Pubblicazione: (2025)

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

Mitigating the Backdoor Effect for Multi-Task Model Merging via Safety-Aware Subspace
di: Yang, Jinluan, et al.
Pubblicazione: (2024)

Stable Nonconvex-Nonconcave Training via Linear Interpolation
di: Pethick, Thomas, et al.
Pubblicazione: (2023)

Optimal Brain Iterative Merging: Mitigating Interference in LLM Merging
di: Wang, Zhixiang, et al.
Pubblicazione: (2025)

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

Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning
di: Aakanksha, et al.
Pubblicazione: (2024)

From Task-Specific Models to Unified Systems: A Review of Model Merging Approaches
di: Ruan, Wei, et al.
Pubblicazione: (2025)

Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
di: Sun, Wenju, et al.
Pubblicazione: (2025)

Bilinear Coordinate Alignment for Training-Free Task-Vector Transfer
di: Son, Jungyong, et al.
Pubblicazione: (2026)

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

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

Computational Budget Should Be Considered in Data Selection
di: Wan, Weilin, et al.
Pubblicazione: (2025)

Conditional Rectified Flow-based End-to-End Rapid Seismic Inversion Method
di: Xu, Haofei, et al.
Pubblicazione: (2026)

Data-Free Layer-Adaptive Merging via Fisher Information for Long-to-Short Reasoning LLMs
di: Xia, Tian
Pubblicazione: (2026)