Related papers: Towards Minimizing Feature Drift in Model Merging:…

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible…

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance…

Model merging combines knowledge from task-specific models into a unified multi-task model to avoid joint training on all task data. However, current methods face challenges due to representation bias, which can interfere with tasks…

Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original training data. Despite recent progress, the reliability of MM under…

Data mixing--the strategic reweighting of training domains--is a critical component in training robust machine learning models. This problem is naturally formulated as a bilevel optimization task, where the outer loop optimizes domain…

Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…

Foundation models have shown outstanding performance and generalization capabilities across domains. Since most studies on foundation models mainly focus on the pretraining phase, a naive strategy to minimize a single task-specific loss is…

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to…

Visual retrieval system faces frequent model update and deployment. It is a heavy workload to re-extract features of the whole database every time.Feature compatibility enables the learned new visual features to be directly compared with…

In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbone sharing, knowledge distillation) often hinge on shared…

Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without…

In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple…

Software fault localization remains challenging due to limited feature diversity and low precision in traditional methods. This paper proposes a novel approach that integrates multi-objective optimization with deep learning models to…

As an effective approach to equip models with multi-task capabilities without additional training, model merging has garnered significant attention. However, existing methods face challenges of redundant parameter conflicts and the…

Standard representational similarity methods align each layer of a network to its best match in another independently, producing asymmetric results, lacking a global alignment score, and struggling with networks of different depths. These…

Multi-view clustering (MVC) optimally integrates complementary information from different views to improve clustering performance. Although demonstrating promising performance in various applications, most of existing approaches directly…

Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscape or rely on intractable full-space Hessian approximations.…

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstrated the effectiveness of combining parameters through…

Merging finetuned Large Language Models (LLMs) has become increasingly important for integrating diverse capabilities into a single unified model. However, prevailing model merging methods rely on linear arithmetic in Euclidean space, which…