English
Related papers

Related papers: Orthogonal Finetuning Made Scalable

200 papers

Large language models (LLMs) have made exciting achievements across various domains, yet their deployment on resource-constrained personal devices remains hindered by the prohibitive computational and memory demands of task-specific…

Machine Learning · Computer Science 2025-06-02 Hong Huang , Dapeng Wu

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all…

Computation and Language · Computer Science 2024-10-14 Changhun Lee , Jun-gyu Jin , Younghyun Cho , Eunhyeok Park

The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results. However, the scaling up of large foundation models has led to soaring costs in…

Machine Learning · Computer Science 2024-12-30 Chongjie Si , Xiaokang Yang , Wei Shen

Recent work has highlighted several advantages of enforcing orthogonality in the weight layers of deep networks, such as maintaining the stability of activations, preserving gradient norms, and enhancing adversarial robustness by enforcing…

Machine Learning · Computer Science 2021-04-19 Asher Trockman , J. Zico Kolter

Point cloud foundation models demonstrate strong generalization, yet adapting them to downstream tasks remains challenging in low-data regimes. Full fine-tuning often leads to overfitting and significant drift from pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Sneha Paul , Zachary Patterson , Nizar Bouguila

Popular parameter-efficient fine-tuning (PEFT) methods, such as LoRA and its variants, freeze pre-trained model weights \(W\) and inject learnable matrices \(\Delta W\). These \(\Delta W\) matrices are structured for efficient…

An alternative to the matrix inverse procedure is presented. Given a bit register which is arbitrarily large, the matrix inverse to an arbitrarily large matrix can be peformed in ${\cal O}(N^2)$ operations, and to matrix multiplication on a…

General Physics · Physics 2007-05-23 Gordon Chalmers

Efficiently adapting large foundation models is critical, especially with tight compute and memory budgets. Parameter-Efficient Fine-Tuning (PEFT) methods such as LoRA offer limited granularity and effectiveness in few-parameter regimes. We…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Ahmet Bilican , M. Akın Yılmaz , A. Murat Tekalp , R. Gökberk Cinbiş

Explorations in fine-tuning Vision-Language Models (VLMs), such as Low-Rank Adaptation (LoRA) from Parameter Efficient Fine-Tuning (PEFT), have made impressive progress. However, most approaches rely on explicit weight updates, overlooking…

Machine Learning · Computer Science 2025-12-30 Mingyuan Zhang , Yue Bai , Yifan Wang , Yiyang Huang , Yun Fu

Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous…

Computer Vision and Pattern Recognition · Computer Science 2025-12-02 Manish Dhakal , Venkat R. Dasari , Rajshekhar Sunderraman , Yi Ding

Deep convolutional neural networks are hindered by training instability and feature redundancy towards further performance improvement. A promising solution is to impose orthogonality on convolutional filters. We develop an efficient…

Computer Vision and Pattern Recognition · Computer Science 2020-04-09 Jiayun Wang , Yubei Chen , Rudrasis Chakraborty , Stella X. Yu

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable…

Computer Vision and Pattern Recognition · Computer Science 2023-11-29 Dongshuo Yin , Xueting Han , Bin Li , Hao Feng , Jing Bai

Standard negative log-likelihood (NLL) for Supervised Fine-Tuning (SFT) applies uniform token-level weighting. This rigidity creates a two-fold failure mode: (i) overemphasizing low-probability targets can amplify gradients on noisy…

Computation and Language · Computer Science 2026-02-13 Zecheng Wang , Deyuan Liu , Chunshan Li , Yupeng Zhang , Zhengyun Zhao , Dianhui Chu , Bingning Wang , Dianbo Sui

Modern processors deliver higher throughput for lower-precision arithmetic than for higher-precision arithmetic. For matrix multiplication, the Ozaki scheme exploits this performance gap by splitting the inputs into lower-precision…

Mathematical Software · Computer Science 2026-04-01 Shota Kawakami , Daisuke Takahashi

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Computation and Language · Computer Science 2025-02-03 Antoine Simoulin , Namyong Park , Xiaoyi Liu , Grey Yang

Automated analysis of optical coherence tomography (OCT) and OCT angiography (OCTA) images is critical for robust ophthalmic diagnosis. Existing mainstream methods trained from scratch rely heavily on massive data and model scale, thereby…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Xiaofei Su , Zengshuo Wang , Minghe Sun , Xin Zhao , Mingzhu Sun

In a rapidly growing field of model training there is a constant practical interest in parameter-efficient fine-tuning and various techniques that use a small amount of training data to adapt the model to a narrow task. However, there is an…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Ali Aliev , Kamil Garifullin , Nikolay Yudin , Vera Soboleva , Alexander Molozhavenko , Ivan Oseledets , Aibek Alanov , Maxim Rakhuba

Parameter-efficient fine-tuning(PEFT) has largely focused on LoRA and its accuracy-oriented variants, leaving the original goal of reducing trainable parameters has receivedcomparatively little attention. We introduce FoRA, which revisits…

Computation and Language · Computer Science 2026-05-29 Juneyoung Park , Seongbae Lee , Han-Sang Lee , Kyuho Lee , Minjae Kim , Seungheon Hyeon , Kiduk Kwon , Seongwan Kim , Jaeho Lee

As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…

Computer Vision and Pattern Recognition · Computer Science 2024-02-06 Otniel-Bogdan Mercea , Alexey Gritsenko , Cordelia Schmid , Anurag Arnab

Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this challenge, Reparameterized Orthogonal Equivalence Training (POET), a spectrum-preserving framework…

Machine Learning · Computer Science 2026-03-06 Zeju Qiu , Lixin Liu , Adrian Weller , Han Shi , Weiyang Liu