SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models

• URL: http://arxiv.org/abs/2606.10617v1
• Date: Tue, 09 Jun 2026 09:16:17 GMT
• Title: SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion Models
• Abstract summary: Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model.<n>Existing LoRA merging techniques often suffer from severe parameter interference, causing destructive collisions in the shared parameter space.<n>We propose Subspace Signal Routing (SSR), which resolves interference by routing internal signals instead of performing parameter-space merge.
• Score: 27.413287599101327
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, existing LoRA merging techniques often suffer from severe parameter interference, causing destructive collisions in the shared parameter space. To address this, we propose Subspace Signal Routing (SSR), which resolves interference by routing internal signals instead of performing parameter-space merge. Specifically, SSR first constructs a unified subspace by concatenating candidate LoRAs along the rank dimension. Next, SSR employs an inverse correlation matrix to decorrelate mixed signals within this space. Finally, a directional guide matrix steers these purified signals into their respective task-specific subspaces. We provide a rigorous theoretical analysis proving that SSR aligns with the Ordinary Least Squares (OLS) solution, thereby ensuring mathematical optimality. We utilize the additivity of sufficient statistics to design a streaming algorithm. This enables on-the-fly updates that significantly reduce memory overhead and computation time. Extensive experiments validate that SSR significantly outperforms state-of-the-art methods while maintaining comparable efficiency. Code is available at https://github.com/nagara214/SSR-Merge.

Related papers

• A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination [51.06539604709775]
  We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views.<n>A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory.
  arXiv  Detail & Related papers  (2026-08-05T14:01:10Z)
• Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning [29.371418314402565]
  heterogeneous clients can make adapter aggregation unstable.<n>We propose Dynamic Subspace Boosting (Dysco) to allocate client-specific LoRA subspaces.<n>Dysco substantially reduces interference, reduces the final-round synthetic training loss by up to 9 times.
  arXiv  Detail & Related papers  (2026-07-15T21:15:35Z)
• SOS-LoRA: Static Orthogonal-Subspace Low-Rank Adaptation with Fixed Multi-Scale Scaling [17.873016968298483]
  Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning (PEFT) method for large language models.<n>We propose Static Orthogonal Subspace LoRA (SOS-LoRA), a drop-in extension that re parameterizes a rank-rtot update as a sum of K static experts.
  arXiv  Detail & Related papers  (2026-06-27T03:25:36Z)
• SMoA: Spectrum Modulation Adapter for Parameter-Efficient Fine-Tuning [57.85676271833619]
  Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full parameter fine-tuning.<n>As the rank increases, more principal singular directions are preserved, which generally improves the model's performance.<n>We propose SMoA, a textbfSpectrum textbfModulation textbfAdapter that enlarges the accessible family of spectrum-aware updates.
  arXiv  Detail & Related papers  (2026-05-20T13:19:28Z)
• Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy [50.63908869296697]
  Merging multiple Low-Rank Adaptation (LoRA) modules is promising for constructing general-purpose systems.<n>We propose TARA-Merging, which aligns merging weights using a preference-weighted cross-entropy pseudo-loss.<n>Across eight vision and six NLI benchmarks, TARA-Merging consistently outperforms vanilla and LoRA-aware baselines.
  arXiv  Detail & Related papers  (2026-03-27T11:07:46Z)
• Beyond SGD, Without SVD: Proximal Subspace Iteration LoRA with Diagonal Fractional K-FAC [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>In this work, we address the gap between training with full steps with low-rank projections (SVDLoRA) and LoRA fine-tuning.<n>We propose LoRSum, a memory-efficient subroutine that closes this gap for gradient descent.
  arXiv  Detail & Related papers  (2026-02-18T13:41:41Z)
• HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance [27.391727025825546]
  Low-Rank Adaptation (LoRA) has emerged as a promising approach to fine-tuning large language models.<n>We propose HyperAdaLoRA, a novel framework that accelerates the convergence of AdaLoRA by leveraging a hypernetwork.<n>Our method achieves faster convergence without sacrificing performance.
  arXiv  Detail & Related papers  (2025-10-03T00:15:59Z)
• Faster Than SVD, Smarter Than SGD: The OPLoRA Alternating Update [50.36542772932594]
  Low-Rank Adaptation (LoRA) fine-tunes large models by learning low-rank updates on top of frozen weights.<n>There is still a gap between full training with low-rank projections (SVDLoRA) and LoRA fine-tuning, indicating that LoRA steps can be further improved.
  arXiv  Detail & Related papers  (2025-09-24T10:32:50Z)
• Regularizing Subspace Redundancy of Low-Rank Adaptation [54.473090597164834]
  We propose ReSoRA, a method that explicitly models redundancy between mapping subspaces and adaptively Regularizes Subspace redundancy of Low-Rank Adaptation.<n>Our proposed method consistently facilitates existing state-of-the-art PETL methods across various backbones and datasets in vision-language retrieval and standard visual classification benchmarks.<n>As a training supervision, ReSoRA can be seamlessly integrated into existing approaches in a plug-and-play manner, with no additional inference costs.
  arXiv  Detail & Related papers  (2025-07-28T11:52:56Z)
• Uni-LoRA: One Vector is All You Need [21.893406288629734]
  Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models.<n>Recent works such as Tied-LoRA, VeRA, and VB-LoRA push efficiency further by introducing additional constraints to reduce the trainable parameter space.<n>We show that the parameter space reduction strategies employed by these LoRA variants can be formulated within a unified framework, Uni-LoRA.
  arXiv  Detail & Related papers  (2025-06-01T03:00:09Z)
• SRLoRA: Subspace Recomposition in Low-Rank Adaptation via Importance-Based Fusion and Reinitialization [2.594346658179846]
  Low-Rank Adaptation (LoRA) constrains updates to a fixed low-rank subspace.<n>We introduce Subspace Recomposition in Low-Rank Adaptation (SRLoRA) via importance-based fusion and reinitialization.<n> SRLoRA consistently achieves faster convergence and improved accuracy over standard LoRA.
  arXiv  Detail & Related papers  (2025-05-18T14:12:40Z)
• Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape [52.98187034726091]
  We introduce Flat-LoRA, which aims to identify a low-rank adaptation situated in a flat region of the full parameter space.<n>We show that Flat-LoRA improves both in-domain and out-of-domain generalization.
  arXiv  Detail & Related papers  (2024-09-22T11:24:10Z)

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.