Skip to content
aiqbenchAI & Quantum Intelligence
NewsInsightsBenchmarksSkillsAsk AILearnAbout
...Loading your session
NewsInsightsBenchmarksSkillsAsk AILearnAbout
Back to list
aiqbench takeMachine Learning

aiqbench analysis

LOFT introduces a unified mathematical framework for orthogonal parameter-efficient fine-tuning (PEFT) by explicitly decoupling subspace rotation from transformation mechanics. By integrating task-aware support selection strategies, the method demonstrates improved performance across diverse benchmarks like language understanding and mathematical reasoning while maintaining strict parameter budgets. This work advances the theoretical understanding of how to optimize low-rank adaptations without conflating distinct design choices in PEFT architectures.
1
Source coveringarXiv

LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection

arXiv·November 13, 2026·2 min read

From arXiv

Full text

arXiv:2605.11872v2 Announce Type: replace Abstract: Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in which adaptation occurs and the transformation applied within that subspace. This paper introduces LOFT, a low-rank orthogonal fine-tuning framework that explicitly separates these two components. By viewing orthogonal adaptation as a multiplicative subspace rotation, LOFT provides a unified formulation that recovers the multiplicative core of representative orthogonal PEFT methods, including coordinate-, butterfly-, Householder- (with a learnable support) and principal-subspace-based variants (up to scaling and relaxation).

More importantly, this perspective exposes support selection as a central design axis rather than a byproduct of a particular parameterization. We develop a first-order analysis showing that useful adaptation supports should be informed by the downstream training signal, motivating practical task-aware support selection strategies. Across language understanding, visual transfer, mathematical reasoning, and multilingual out-of-distribution adaptation, LOFT with task-aware supports improves performance at matched trainable-parameter and transform settings under a shared protocol. This suggests that, under a fixed transform and budget, the choice of support affects performance, making systematic support selection an important direction for improving orthogonal PEFT.

Abstract:Orthogonal parameter-efficient fine-tuning (PEFT) adapts pretrained weights through structure-preserving multiplicative transformations, but existing methods often conflate two distinct design choices: the subspace in which adaptation occurs and the transformation applied within that subspace. This paper introduces LOFT, a low-rank orthogonal fine-tuning framework that explicitly separates these two components. By viewing orthogonal adaptation as a multiplicative subspace rotation, LOFT provides a unified formulation that recovers the multiplicative core of representative orthogonal PEFT methods, including coordinate-, butterfly-, Householder- (with a learnable support) and principal-subspace-based variants (up to scaling and relaxation).

More importantly, this perspective exposes support selection as a central design axis rather than a byproduct of a particular parameterization. We develop a first-order analysis showing that useful adaptation supports should be informed by the downstream training signal, motivating practical task-aware support selection strategies. Across language understanding, visual transfer, mathematical reasoning, and multilingual out-of-distribution adaptation, LOFT with task-aware supports improves performance at matched trainable-parameter and transform settings under a shared protocol. This suggests that, under a fixed transform and budget, the choice of support affects performance, making systematic support selection an important direction for improving orthogonal PEFT.

Accepted at NeurIPS 2026. Camera-ready version

Machine Learning (cs.LG); Machine Learning (stat.ML)

arXiv:2605.11872 [cs.LG]

(or arXiv:2605.11872v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.11872 Focus to learn more arXiv-issued DOI via DataCite

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.

Full text under the publisher's open licence · 286 words

Read at arXiv ↗Ask about this article

Related coverage

Machine Learning

Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives

arXiv · Aug 20, 2026

AI Research

Pre-Training for Simulation-Based Science: A Study on Jet Foundation Model Training Objectives

arXiv · Jun 16, 2026

Machine Learning

PoLoRA: A Preconditioned Orthogonalized LoRA Optimizer

arXiv · Jul 21, 2026

AI Research

CORAM: Coherent Orthogonal Rotation for Model Merging

arXiv · Aug 20, 2026

Article info

Source

arXiv

Published

November 13, 2026

Read time

2 min

Category

Machine Learning
aiqbench
AI & Quantum Intelligence© aiqbench. All rights reserved.

Feeds:RSS·JSON Feed

LanguageEnglish·Românăbeta
NewsAI & TechQuantumInsights
ExploreBenchmarksLearn
CompanyAboutTrustLegal noticeTerms of ServicePrivacy PolicyCopyright noticesData erasureReport content

The aiqbench take, the insights, the daily digest and Ask answers are written by AI models from the sources shown, without editorial review before publication. They may contain errors — check the source. How the model is used →

  • News
  • Insights
  • Ask AI
  • Benchmarks
  • Account