When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging

• URL: http://arxiv.org/abs/2608.27518v1
• Date: Thu, 27 Aug 2026 10:56:58 GMT
• Title: When Muon Meets Task Interference: A Spectral Perspective on Continual Learning and Model Merging
• Abstract summary: We show that the two difficulties are in fact two instances of the same phenomenon.<n>A parameter update useful for one task shifts the model's outputs on another.<n>We identify the recent Muon as a mechanism that regulates this factor by construction.
• Score: 32.67767249149513
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Continual learning (CL) and model merging (MM) both aim to obtain a single model that performs well across multiple tasks, challenged respectively by catastrophic forgetting and weight-disentanglement error. In the literature, these difficulties are merely treated separately and mitigated through a variety of solutions, while the geometry induced by the base optimizer is treated as an implementation detail. In this work, we show that the two difficulties are in fact two instances of the same phenomenon: a parameter update useful for one task shifts the model's outputs on another. We formalize this shared phenomenon as \textit{task interference} and reduce it to a common layer-wise Frobenius inner product $\langle ΔW_\ell, J_\ell(x)\rangle_F$. This quantity, in turn, is utilized to expose the role of the optimizer. We theoretically derive an upper bound that isolates the spectral norm $\|ΔW_\ell\|_2$ as an optimizer-controllable factor of task interference, and a per-mode analysis shows that this bound tracks the dominant part of the empirical interference. Specifically, we then identify the recent Muon optimizer as a mechanism that regulates this factor by construction. Our work reveals that its elegant control on spectral norm tightens the interference bound for both CL and MM, positioning Muon as a principled optimizer-centric approach complementary to existing solutions. Our theoretcal analysis is well validated by experimental results. Replacing the AdamW optimizer with Muon improves accuracy by up to +5.02 points on the eight-task model-merging benchmark across three CLIP backbones. For continual learning, Muon also delivers uniformly positive gains across ten class-incremental protocols, three task-incremental protocols, and the 11-task MTIL benchmark.

Related papers

• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• MTL-FNO: A Lightweight Multi-Task Fourier Neural Operator for Sparse Field Reconstruction [15.401658861451809]
  Multi-task Fourier neural operator (MTL-FNO) is an end-to-end joint training framework based on hard parameter sharing.<n> MTL-FNO achieves accuracy comparable to or even surpassing that of standard FNO, while reducing total model size by 76% and 60%, respectively.<n>Results show that MTL-FNO achieves accuracy comparable to or even surpassing that of standard FNO, while reducing total model size by 76% and 60%, respectively.
  arXiv  Detail & Related papers  (2026-05-26T08:57:31Z)
• Optimizer-Induced Mode Connectivity: From AdamW to Muon [50.258866851760416]
  We show that solutions from a single -- AdamW, Muon, or others in the Lion-$mathcalK$ family -- form a connected set at sufficiently large width.<n>We then characterize how-induced regions interact: at large width two different regions can be disjoint or overlap depending on regularization.
  arXiv  Detail & Related papers  (2026-05-11T05:07:36Z)
• MAny: Merge Anything for Multimodal Continual Instruction Tuning [52.50936513604062]
  textbfMAny (textbfMAny) is a framework that merges task-specific knowledge through textbfCross-modal textbfProjection textbfMerging.<n>textbfLow-rank textbfParameter textbfMerging (textbfLPM)
  arXiv  Detail & Related papers  (2026-04-15T15:57:23Z)
• Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration [14.503741632243646]
  Multi-task model merging aims to consolidate knowledge from multiple task-specific experts into a unified model.<n>Existing methods approach this by minimizing differences between task-specific experts and the unified model.<n>We propose Layer-wise Optimal Task Vector Merging, a technique that explicitly minimizes feature drift between task-specific experts and the unified model.
  arXiv  Detail & Related papers  (2025-05-29T08:11:31Z)
• Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning [57.514786046966265]
  We propose textbfPerturb-and-Merge (P&M), a novel continual learning framework that integrates model merging into the CL paradigm to mitigate forgetting.<n>Our proposed approach achieves state-of-the-art performance on several continual learning benchmark datasets.
  arXiv  Detail & Related papers  (2025-05-28T14:14:19Z)
• SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery [54.866490321241905]
  Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models. In this paper, we examine the merged model's representation distribution and uncover a critical issue of "representation bias" This bias arises from a significant distribution gap between the representations of the merged and expert models, leading to the suboptimal performance of the merged MTL model.
  arXiv  Detail & Related papers  (2024-10-18T11:49:40Z)
• AdaMerging: Adaptive Model Merging for Multi-Task Learning [68.75885518081357]
  This paper introduces an innovative technique called Adaptive Model Merging (AdaMerging) It aims to autonomously learn the coefficients for model merging, either in a task-wise or layer-wise manner, without relying on the original training data. Compared to the current state-of-the-art task arithmetic merging scheme, AdaMerging showcases a remarkable 11% improvement in performance.
  arXiv  Detail & Related papers  (2023-10-04T04:26:33Z)
• A conditional one-output likelihood formulation for multitask Gaussian processes [0.0]
  Multitask Gaussian processes (MTGP) are the Gaussian process framework's solution for multioutput regression problems. Here we introduce a novel approach that simplifies the multitask learning. We show that it is computationally competitive with state of the art options.
  arXiv  Detail & Related papers  (2020-06-05T14:59:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.