Skip to content
AI News HubLIVE
Original source2 min read

CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

Summary

As large pre-trained models scale up, fine-tuning under limited memory becomes challenging. LoRA reduces learnable parameters via low-rank matrices, but activation storage remains a bottleneck. CARE-LoRA replaces full input activations with low-rank compressed activations from the LoRA branch, and computes a lightweight reconstruction matrix for backpropagation, substantially reducing memory while maintaining or improving performance.

SourcearXiv Machine LearningAuthor: Gengyu Zhang, Haiyin Ran, Zhengbao He, Yuhang Liu, Hanling Tian, Zhehao Huang, Xiaolin Huang
CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 11 Jul 2026]

Title:CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA

View a PDF of the paper titled CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA, by Gengyu Zhang and 6 other authors

View PDF HTML (experimental)

Abstract:As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently one of the most widely adopted parameter-efficient fine-tuning (PEFT) methods, mitigates this challenge by optimizing only low-rank adaptation matrices, thereby greatly reducing the number of trainable parameters. With the parameter overhead substantially reduced, the activations retained for backpropagation have emerged as the primary remaining memory bottleneck during LoRA fine-tuning. To address this, we propose CARE-LoRA, a data-aware Compressed Activation REconstruction framework. By exploiting the inherent projection structure of LoRA, CARE-LoRA replaces the full input activation with the low-rank compressed activation naturally produced by the LoRA branch. It further computes a lightweight reconstruction matrix during the forward pass with negligible additional computation cost, which is used during backpropagation to reconstruct the gradient signal, thereby keeping LoRA matrices fully trainable. Extensive experiments across diverse models and downstream tasks demonstrate that, while substantially reducing the overall memory footprint, CARE-LoRA achieves competitive or even superior performance compared with standard LoRA and representative LoRA variants. Our code is publicly available at this https URL .

Comments: 15 pages, 2 figures, 12 tables. Code available at this https URL

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2607.11940 [cs.LG]

(or arXiv:2607.11940v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.11940

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Gengyu Zhang [view email] [v1] Sat, 11 Jul 2026 09:04:58 UTC (124 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled CARE-LoRA: Compressed Activation REconstruction for Memory-Efficient LoRA, by Gengyu Zhang and 6 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-07

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • CARE-LoRA addresses the activation memory bottleneck in LoRA fine-tuning via compressed activation reconstruction.
  • It leverages the naturally low-rank activations from the LoRA branch to replace full activations, reducing storage.
  • A lightweight reconstruction matrix is computed during forward pass and used for gradient recovery, incurring minimal overhead.
  • Experiments show 30-50% peak memory reduction with competitive or superior performance compared to standard LoRA.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models