Saved in:
Bibliographic Details
Main Authors: Qiu, Haiyun, Wu, Xingyu, Tan, Kay Chen
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.22464
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915955124207616
author Qiu, Haiyun
Wu, Xingyu
Tan, Kay Chen
author_facet Qiu, Haiyun
Wu, Xingyu
Tan, Kay Chen
contents Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation and representation interference within fixed capacities, whereas Mixture-of-Experts (MoE) variants resort to indiscriminate expansion, incurring expert redundancy and a routing bottleneck reliant on additional data-driven optimization. To resolve these challenges, we propose MADE-IT (Manifold-Aware Dynamic Expert Evolution and Implicit rouTing), an adaptive CMM method that orchestrates expert management and activation by grounding intrinsic expert representations in manifold geometry. We introduce a projection-based subspace affinity metric coupled with a distribution-aware adaptive threshold mechanism to guide autonomous expert evolution, harmonizing diversity with architectural parsimony. Furthermore, to bypass parameterized gating networks, we design a data-free and training-free implicit routing mechanism that activates experts via feature-subspace alignment. Extensive experiments demonstrate that MADE-IT consistently outperforms strong baselines in accuracy and robustness across long-horizon and shuffled task sequences, while significantly pruning redundant experts, particularly within generic modules and early layers.
format Preprint
id arxiv_https___arxiv_org_abs_2604_22464
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Adaptive Continual Model Merging via Manifold-Aware Expert Evolution
Qiu, Haiyun
Wu, Xingyu
Tan, Kay Chen
Machine Learning
Continual Model Merging (CMM) sequentially integrates task-specific models into a unified architecture without intensive retraining. However, existing CMM methods are hindered by a fundamental saturation-redundancy dilemma: backbone-centric approaches face parameter saturation and representation interference within fixed capacities, whereas Mixture-of-Experts (MoE) variants resort to indiscriminate expansion, incurring expert redundancy and a routing bottleneck reliant on additional data-driven optimization. To resolve these challenges, we propose MADE-IT (Manifold-Aware Dynamic Expert Evolution and Implicit rouTing), an adaptive CMM method that orchestrates expert management and activation by grounding intrinsic expert representations in manifold geometry. We introduce a projection-based subspace affinity metric coupled with a distribution-aware adaptive threshold mechanism to guide autonomous expert evolution, harmonizing diversity with architectural parsimony. Furthermore, to bypass parameterized gating networks, we design a data-free and training-free implicit routing mechanism that activates experts via feature-subspace alignment. Extensive experiments demonstrate that MADE-IT consistently outperforms strong baselines in accuracy and robustness across long-horizon and shuffled task sequences, while significantly pruning redundant experts, particularly within generic modules and early layers.
title Towards Adaptive Continual Model Merging via Manifold-Aware Expert Evolution
topic Machine Learning
url https://arxiv.org/abs/2604.22464