Cover Image

M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Tiantong, Duan, Yiyang, Chen, Haoyu, Wu, Tiantong, Lim, Wei Yang Bryan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models
by: Wang, Tiantong, et al.
Published: (2026)

Oblivionis: A Lightweight Learning and Unlearning Framework for Federated Large Language Models
by: Zhang, Fuyao, et al.
Published: (2025)

Enhancing Federated Domain Adaptation with Multi-Domain Prototype-Based Federated Fine-Tuning
by: Zhang, Jingyuan, et al.
Published: (2024)

LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
by: Geng, Chuanxing, et al.
Published: (2025)

Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data
by: Mishra, Aayush, et al.
Published: (2025)

On Leveraging Unlabeled Data for Concurrent Positive-Unlabeled Classification and Robust Generation
by: Yu, Bing, et al.
Published: (2020)

Learning from M-Tuple Dominant Positive and Unlabeled Data
by: Qin, Jiahe, et al.
Published: (2025)

One-dimensional polarization-hybrid photonic crystal molecules
by: Li, Tiantong, et al.
Published: (2026)

The indivisibility of a quantum-corrected AdS black hole with phantom global monopoles
by: Cheng, Tiantong, et al.
Published: (2026)

Learning from Uncertain Similarity and Unlabeled Data
by: Wei, Meng, et al.
Published: (2025)

PUAL: A Classifier on Trifurcate Positive-Unlabeled Data
by: Wang, Xiaoke, et al.
Published: (2024)

Semi-Supervised Crowd Counting from Unlabeled Data
by: Duan, Haoran, et al.
Published: (2021)

Adapting to Shifting Correlations with Unlabeled Data Calibration
by: Nguyen, Minh, et al.
Published: (2024)

Deep Positive-Unlabeled Anomaly Detection for Contaminated Unlabeled Data
by: Takahashi, Hiroshi, et al.
Published: (2024)

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers
by: Liu, Renpu, et al.
Published: (2026)

Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model
by: He, Rundong, et al.
Published: (2025)

Proper Learnability and the Role of Unlabeled Data
by: Asilis, Julian, et al.
Published: (2025)

Positive and Unlabeled Data: Model, Estimation, Inference, and Classification
by: Liu, Siyan, et al.
Published: (2024)

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

Augmenting Offline RL with Unlabeled Data
by: Wang, Zhao, et al.
Published: (2024)

Unlabeled Data vs. Pre-trained Knowledge: Rethinking SSL in the Era of Large Models
by: Lv, Song-Lin, et al.
Published: (2025)

Collaborative Unlabeled Data Optimization
by: Shang, Xinyi, et al.
Published: (2025)

Model Merging on Loss Landscape: A Geometry Perspective
by: Lu, Juanwu, et al.
Published: (2026)

Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
by: Wang, Wei, et al.
Published: (2025)

Coupled Training with Privileged Information and Unlabeled Data
by: Shi, Jiahao, et al.
Published: (2026)

LAUD: Integrating Large Language Models with Active Learning for Unlabeled Data
by: Chou, Tzu-Hsuan, et al.
Published: (2025)

Heterogeneous Domain Adaptation with Positive and Unlabeled Data
by: Mori, Junki, et al.
Published: (2023)

Out-Of-Domain Unlabeled Data Improves Generalization
by: Saberi, Amir Hossein, et al.
Published: (2023)

Offline Reinforcement Learning with Domain-Unlabeled Data
by: Nishimori, Soichiro, et al.
Published: (2024)

Sample-Optimal Agnostic Boosting with Unlabeled Data
by: Ghai, Udaya, et al.
Published: (2025)

CATCHFed: Efficient Unlabeled Data Utilization for Semi-Supervised Federated Learning in Limited Labels Environments
by: Park, Byoungjun, et al.
Published: (2025)

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

Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
by: Yang, Jinluan, et al.
Published: (2025)

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

AllMatch: Exploiting All Unlabeled Data for Semi-Supervised Learning
by: Wu, Zhiyu, et al.
Published: (2024)

Positive-Unlabeled Reinforcement Learning Distillation for On-Premise Small Models
by: Kou, Zhiqiang, et al.
Published: (2026)

Heterogeneous Multisource Transfer Learning via Model Averaging for Positive-Unlabeled Data
by: Liu, Jialei, et al.
Published: (2025)

How to Craft Backdoors with Unlabeled Data Alone?
by: Wang, Yifei, et al.
Published: (2024)

Positive-Unlabeled Diffusion Models for Preventing Sensitive Data Generation
by: Takahashi, Hiroshi, et al.
Published: (2025)

FedAnchor: Enhancing Federated Semi-Supervised Learning with Label Contrastive Loss for Unlabeled Clients
by: Qiu, Xinchi, et al.
Published: (2024)