The Appeal and Reality of Recycling LoRAs with Adaptive Merging

• URL: http://arxiv.org/abs/2602.12323v1
• Date: Thu, 12 Feb 2026 18:59:20 GMT
• Title: The Appeal and Reality of Recycling LoRAs with Adaptive Merging
• Authors: Haokun Liu, Gyung Hyun Je, Marco Ciccone, Zhenlin Xu, Prasanth YSS, Colin Raffel,
• Abstract summary: We consider recycling LoRAs found "in the wild" on model repositories like the Hugging Face Hub.<n>We demonstrate that adaptive merging methods can improve performance over the base model but provide limited benefit over training a new LoRA.<n>This raises the possibility that adaptive merging from recycled LoRAs primarily works via some kind of regularization effect.
• Score: 33.0501514389443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The widespread availability of fine-tuned LoRA modules for open pre-trained models has led to an interest in methods that can adaptively merge LoRAs to improve performance. These methods typically include some way of selecting LoRAs from a pool and tune merging coefficients based on a task-specific dataset. While adaptive merging methods have demonstrated improvements in some settings, no past work has attempted to recycle LoRAs found "in the wild" on model repositories like the Hugging Face Hub. To address this gap, we consider recycling from a pool of nearly 1,000 user-contributed LoRAs trained from the Llama 3.1 8B-Instruct language model. Our empirical study includes a range of adaptive and non-adaptive merging methods in addition to a new method designed via a wide search over the methodological design space. We demonstrate that adaptive merging methods can improve performance over the base model but provide limited benefit over training a new LoRA on the same data used to set merging coefficients. We additionally find not only that the specific choice of LoRAs to merge has little importance, but that using LoRAs with randomly initialized parameter values yields similar performance. This raises the possibility that adaptive merging from recycled LoRAs primarily works via some kind of regularization effect, rather than by enabling positive cross-task transfer. To better understand why past work has proven successful, we confirm that positive transfer is indeed possible when there are highly relevant LoRAs in the pool. We release the model checkpoints and code online.

Related papers

• 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)
• Dual LoRA: Enhancing LoRA with Magnitude and Direction Updates [14.49537642990529]
  Low-rank adaptation (LoRA) is one of the most popular methods among parameter-efficient fine-tuning (PEFT)<n>We propose a novel method called Dual LoRA to improve the performance by incorporating an inductive bias into the original LoRA.<n>We show that we consistently outperform LoRA and its state-of-the-art variants with the same number of trainable parameters.
  arXiv  Detail & Related papers  (2025-12-03T03:14:09Z)
• 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)
• Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation [9.156064716689833]
  The LoRA merge technique integrates multiple LoRA modules trained on different tasks.<n>Previous methods are limited in adaptability as they keep the LoRA parameters frozen.<n>We propose a LoRA merge method that updates and prunes LoRA parameters through fine-tuning with minimal target task data.
  arXiv  Detail & Related papers  (2025-05-30T03:34:25Z)
• SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning [73.93639228235622]
  Continual Learning with foundation models has emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks.<n>Existing prompt-based and Low-Rank Adaptation-based (LoRA-based) methods often require expanding a prompt/LoRA pool or retaining samples of previous tasks.<n>We propose Scalable Decoupled LoRA (SD-LoRA) for class incremental learning, which continually separates the learning of the magnitude and direction of LoRA components without rehearsal.
  arXiv  Detail & Related papers  (2025-01-22T20:00:41Z)
• CopRA: A Progressive LoRA Training Strategy [9.847045610578073]
  Low-Rank Adaptation (LoRA) is a parameter-efficient technique for fine-tuning foundation models. In this work, we propose a novel progressive training strategy for LoRA with random layer dropping. We refer to this method as Cooperative LoRA (CopRA)
  arXiv  Detail & Related papers  (2024-10-30T11:07:09Z)
• LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [78.93425154518705]
  Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements.<n>This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization.
  arXiv  Detail & Related papers  (2024-10-27T22:57:12Z)
• FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Foundation Models [5.1613368481802455]
  Low-Rank Adaptation (LoRA) is a popular technique for efficient fine-tuning of foundation models.<n>We propose Federated Exact LoRA, or FedEx-LoRA, which adds a residual error term to the pretrained frozen weight matrix.<n>Our approach achieves exact updates with minimal computational and communication overhead, preserving LoRA's efficiency.
  arXiv  Detail & Related papers  (2024-10-12T08:22:44Z)
• Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation [58.288682735160585]
  Low-Rank Adaptation (LoRA) is a popular technique for finetuning models. LoRA often under performs when compared to full- parameter fine-tuning. We present a framework that rigorously analyzes the adaptation rates of LoRA methods.
  arXiv  Detail & Related papers  (2024-10-10T18:51:53Z)
• Unlocking the Global Synergies in Low-Rank Adapters [20.32980343066711]
  Low-rank Adaption (LoRA) has been the de-facto parameter-efficient fine-tuning technique for large language models. We present HeteroLoRA, a light-weight search algorithm that leverages zero-cost proxies to allocate the limited LoRA trainable parameters. Experiments show that HeteroLoRA enables improvements in model performance given the same parameter budge.
  arXiv  Detail & Related papers  (2024-06-21T08:10:03Z)
• ResLoRA: Identity Residual Mapping in Low-Rank Adaption [96.59370314485074]
  We propose ResLoRA, an improved framework of low-rank adaptation (LoRA) Our method can achieve better results in fewer training steps without any extra trainable parameters or inference cost compared to LoRA. The experiments on NLG, NLU, and text-to-image tasks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-02-28T04:33:20Z)

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.