Cover Image

MAGIC: Achieving Superior Model Merging via Magnitude Calibration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Yayuan, Zhang, Jian, Guo, Jintao, Cheng, Zihan, Qi, Lei, Shi, Yinghuan, Gao, Yang
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
by: Li, Yayuan, et al.
Published: (2026)

Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP
by: Li, Yayuan, et al.
Published: (2024)

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
by: Guo, Jintao, et al.
Published: (2024)

Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations
by: Wang, Na, et al.
Published: (2024)

Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation
by: Cheng, Zihan, et al.
Published: (2025)

SETA: Semantic-Aware Token Augmentation for Domain Generalization
by: Guo, Jintao, et al.
Published: (2024)

Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
by: Hu, Jiajun, et al.
Published: (2024)

One Token, Two Fates: A Unified Framework via Vision Token Manipulation Against MLLMs Hallucination
by: Fa, Zhan, et al.
Published: (2026)

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
by: Qiu, Muyang, et al.
Published: (2024)

Unleashing the Power of Intermediate Domains for Mixed Domain Semi-Supervised Medical Image Segmentation
by: Ma, Qinghe, et al.
Published: (2025)

Diversity-enhanced Collaborative Mamba for Semi-supervised Medical Image Segmentation
by: Li, Shumeng, et al.
Published: (2025)

Duala: Dual-Level Alignment of Subjects and Stimuli for Cross-Subject fMRI Decoding
by: Li, Shumeng, et al.
Published: (2026)

MAGIC: Multimodal Alignment & Grounding-aware Instruction Coreset for Vision-Language Models
by: Biswas, Shristi Das, et al.
Published: (2026)

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

An Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
by: Duan, Yue, et al.
Published: (2025)

NormAUG: Normalization-guided Augmentation for Domain Generalization
by: Qi, Lei, et al.
Published: (2023)

MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization
by: Qi, Lei, et al.
Published: (2022)

Taste More, Taste Better: Diverse Data and Strong Model Boost Semi-Supervised Crowd Counting
by: Yang, Maochen, et al.
Published: (2025)

Correspondence as Video: Test-Time Adaption on SAM2 for Reference Segmentation in the Wild
by: Wang, Haoran, et al.
Published: (2025)

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
by: Cao, Luyang, et al.
Published: (2025)

Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation
by: Ma, Qinghe, et al.
Published: (2025)

Reasoning Resides in Layers: Restoring Temporal Reasoning in Video-Language Models with Layer-Selective Merging
by: Fu, Zihang, et al.
Published: (2026)

Generalizable Metric Network for Cross-domain Person Re-identification
by: Qi, Lei, et al.
Published: (2023)

Patch-aware Batch Normalization for Improving Cross-domain Robustness
by: Qi, Lei, et al.
Published: (2023)

Constructing and Exploring Intermediate Domains in Mixed Domain Semi-supervised Medical Image Segmentation
by: Ma, Qinghe, et al.
Published: (2024)

Balancing Multi-Target Semi-Supervised Medical Image Segmentation with Collaborative Generalist and Specialists
by: Wang, You, et al.
Published: (2025)

Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
by: Li, Shumeng, et al.
Published: (2024)

InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models
by: Liu, Xinxin, et al.
Published: (2026)

Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA
by: Fa, Zhan, et al.
Published: (2026)

MAGIC: Near-Optimal Data Attribution for Deep Learning
by: Ilyas, Andrew, et al.
Published: (2025)

A Novel Cross-Perturbation for Single Domain Generalization
by: Zhao, Dongjia, et al.
Published: (2023)

StableMind: Source-Free Cross-Subject fMRI Decoding with Regularized Adaptation
by: Guo, Jintao, et al.
Published: (2026)

AdaMMS: Model Merging for Heterogeneous Multimodal Large Language Models with Unsupervised Coefficient Optimization
by: Du, Yiyang, et al.
Published: (2025)

Beyond Attention Magnitude: Leveraging Inter-layer Rank Consistency for Efficient Vision-Language-Action Models
by: Liu, Peiju, et al.
Published: (2026)

Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation
by: Li, Zekun, et al.
Published: (2026)

Model Merging to Maintain Language-Only Performance in Developmentally Plausible Multimodal Models
by: Takmaz, Ece, et al.
Published: (2025)

Generalizable Entity Grounding via Assistance of Large Language Model
by: Qi, Lu, et al.
Published: (2024)

WeakMedSAM: Weakly-Supervised Medical Image Segmentation via SAM with Sub-Class Exploration and Prompt Affinity Mining
by: Wang, Haoran, et al.
Published: (2025)

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
by: Gao, Xin, et al.
Published: (2026)

MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models
by: Miao, Yongzhu, et al.
Published: (2023)