Cover Image

Localizing Task Information for Improved Model Merging and Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Ke, Dimitriadis, Nikolaos, Ortiz-Jimenez, Guillermo, Fleuret, François, Frossard, Pascal
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging
by: Wang, Ke, et al.
Published: (2024)

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

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels
by: Wang, Ke, et al.
Published: (2023)

Pareto Low-Rank Adapters: Efficient Multi-Task Learning with Preferences
by: Dimitriadis, Nikolaos, et al.
Published: (2024)

Backdoor Unlearning by Linear Task Decomposition
by: Abdelraheem, Amel, et al.
Published: (2025)

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

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

Semantic Document Derendering: SVG Reconstruction via Vision-Language Modeling
by: Hazimeh, Adam, et al.
Published: (2025)

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

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

Efficient World Models with Context-Aware Tokenization
by: Micheli, Vincent, et al.
Published: (2024)

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

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

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

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

Label-Free Cross-Task LoRA Merging with Null-Space Compression
by: Lee, Wonyoung, et al.
Published: (2026)

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

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

Sequential Representation Learning via Static-Dynamic Conditional Disentanglement
by: Simon, Mathieu Cyrille, et al.
Published: (2024)

Improving EO Foundation Models with Confidence Assessment for enhanced Semantic segmentation
by: Dionelis, Nikolaos, et al.
Published: (2024)

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

AgentCompress: Task-Aware Compression for Affordable Large Language Model Agents
by: Taha, Zuhair Ahmed Khan, et al.
Published: (2026)

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

GrapHist: Graph Self-Supervised Learning for Histopathology
by: Öğüt, Sevda, et al.
Published: (2026)

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
by: Wang, Ke, et al.
Published: (2025)

Saliency-Aware Model Merging
by: Park, Jungin, et al.
Published: (2026)

LLaVA-Zip: Adaptive Visual Token Compression with Intrinsic Image Information
by: Wang, Ke, et al.
Published: (2024)

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

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

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

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

Task Relevance Is Not Local Replaceability: A Two-Axis View of Channel Information
by: Safaai, Houman, et al.
Published: (2026)

Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach
by: Yang, Ruo, et al.
Published: (2024)

WorldPack: Compressed Memory Improves Spatial Consistency in Video World Modeling
by: Oshima, Yuta, et al.
Published: (2025)

Resolving Interference (RI): Disentangling Models for Improved Model Merging
by: Ramesh, Pratik, et al.
Published: (2026)

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

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

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

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

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