Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

• URL: http://arxiv.org/abs/2606.03723v1
• Date: Tue, 02 Jun 2026 14:42:46 GMT
• Title: Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter
• Abstract summary: We study the problem of merging $T$ LoRAs into a single rank-$r$ LoRA.<n>Existing-then-Compress pipelines treat the rank constraint as an afterthought.<n>We propose Compress-then-Merge (CtM), a reversed pipeline that enforces the rank-$r$ bottleneck before merging.
• Score: 31.066992554963093
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapters, complicating reuse and deployment. We study the problem of merging $T$ LoRAs into a single rank-$r$ LoRA, thereby preserving the benefits of low-rank structure. Existing Merge-then-Compress pipelines treat the rank constraint as an afterthought: they merge adapters in the full parameter space, then compress the merged result to rank $r$ via truncated SVD. However, full-parameter merging may destroy the low-rank structure, making it difficult for subsequent compression to recover an effective rank-$r$ LoRA. We propose Compress-then-Merge (CtM), a reversed pipeline that enforces the rank-$r$ bottleneck before merging: CtM computes shared $r$-dimensional subspaces using only the LoRA weights to capture cross-adapter common structure, projects each adapter into the shared subspaces to obtain $r\times r$ coordinates, and then applies standard merging rules in this reduced space. CtM guarantees a rank-$r$ LoRA by construction, avoiding post-hoc truncation, and enables efficient computation in the core space spanned by concatenated LoRA factors. Experiments across multiple models and tasks show that CtM consistently outperforms existing single-LoRA-output baselines while narrowing the performance gap to full-parameter merging methods.

Related papers

• Rethinking Factor Sharing in Federated LoRA: A Rank-Aware Adaptive Approach [58.97285859000893]
  We study whether $A$ should be shared across clients while $B$ remains client-specific (Share-A/Local-B) or whether $B$ should instead be shared while $A$ remains client-specific (Share-B/Local-A)<n>We propose Federated Adaptive Factor Sharing Low-Rank Adaptation (FedAS-LoRA), which selects the sharing side before training to enhance fine-tuning performance.
  arXiv  Detail & Related papers  (2026-08-10T15:38:45Z)
• Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging [29.33065526693412]
  MergePipe is a budget-aware execution layer for weight-space model merging.<n>It reduces expert-read I/O by up to an order of magnitude and achieves up to $11times$ speedups.
  arXiv  Detail & Related papers  (2026-05-28T07:15:38Z)
• Evolutionary Negative Module Pruning for Better LoRA Merging [46.397675691417675]
  Merging multiple Low-Rank Adaptation experts into a single backbone is a promising approach for efficient multi-task deployment.<n>Existing methods strive to alleviate interference via weight or subspace alignment.<n>We propose a plug-and-play LoRA pruning method to locate and exclude these modules prior to merging.
  arXiv  Detail & Related papers  (2026-04-20T03:13:18Z)
• Crowded in B-Space: Calibrating Shared Directions for LoRA Merging [12.949322198287417]
  Merging separately trained LoRA adapters is a practical alternative to joint multi-task training, but it often hurts performance.<n>We show that the main source of LoRA merge interference comes from the output-side matrix $B$.<n>We propose Pico, a data-free method that calibrates $B$ before merge by downscaling over-shared directions and then rescaling the merged update.
  arXiv  Detail & Related papers  (2026-04-18T04:33:16Z)
• 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)
• Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs [26.212332132619736]
  We propose an asymmetric multi-LoRA design with multiple $A$ matrices and a single shared $B$ in multi-task fine-tuning.<n>Our methods achieve more balanced performance across tasks with comparable or superior average accuracy relative to existing multi-LoRA approaches.
  arXiv  Detail & Related papers  (2025-09-29T19:16:14Z)
• 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)
• Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights [75.83625828306839]
  textbfDrag-and-Drop LLMs (textitDnD) eliminates per-task training by mapping a handful of unlabeled task prompts directly to LoRA weight updates.<n>A lightweight text encoder distills each prompt batch into condition embeddings, which are then transformed by a cascaded hyper-convolutional decoder into the full set of LoRA matrices.
  arXiv  Detail & Related papers  (2025-06-19T15:38:21Z)
• 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)
• 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)
• S-LoRA: Serving Thousands of Concurrent LoRA Adapters [59.490751234925206]
  Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, is often employed to adapt a base model to a multitude of tasks. We present S-LoRA, a system designed for the scalable serving of many LoRA adapters.
  arXiv  Detail & Related papers  (2023-11-06T17:26:17Z)

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.