English
Related papers

Related papers: Dataset Size Recovery from LoRA Weights

200 papers

Image restoration has traditionally required training specialized models on thousands of paired examples per degradation type. We challenge this paradigm by demonstrating that powerful pre-trained text-conditioned image editing models can…

Image and Video Processing · Electrical Eng. & Systems 2026-01-21 M. Akın Yılmaz , Ahmet Bilican , Burak Can Biner , A. Murat Tekalp

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

Computation and Language · Computer Science 2024-09-18 Simon Yu , Liangyu Chen , Sara Ahmadian , Marzieh Fadaee

The outcome of Large Language Model (LLM) pre-training strongly depends on weight initialization and variance control strategies. Although the importance of initial variance control has been well documented in neural networks in general,…

Machine Learning · Computer Science 2025-03-25 Louis Owen , Abhay Kumar , Nilabhra Roy Chowdhury , Fabian Güra

It is well known that $\ell_1$ minimization can be used to recover sufficiently sparse unknown signals from compressed linear measurements. In fact, exact thresholds on the sparsity, as a function of the ratio between the system dimensions,…

Information Theory · Computer Science 2011-11-08 M. Amin Khajehnejad , Weiyu Xu , A. Salman Avestimehr , Babak Hassibi

The rapid development of parameter-efficient fine-tuning methods has noticeably improved the efficiency of adapting large language models. Among these, LoRA has gained widespread popularity due to its strong balance of effectiveness and…

Machine Learning · Computer Science 2026-01-15 Yongfu Xue

We propose a novel approach for instance-level image retrieval. It produces a global and compact fixed-length representation for each image by aggregating many region-wise descriptors. In contrast to previous works employing pre-trained…

Computer Vision and Pattern Recognition · Computer Science 2016-07-29 Albert Gordo , Jon Almazan , Jerome Revaud , Diane Larlus

Modern iterations of deep learning models contain millions (billions) of unique parameters, each represented by a b-bit number. Popular attempts at compressing neural networks (such as pruning and quantisation) have shown that many of the…

Machine Learning · Computer Science 2022-10-26 Christopher Subia-Waud , Srinandan Dasmahapatra

Image reconstruction using deep learning algorithms offers improved reconstruction quality and lower reconstruction time than classical compressed sensing and model-based algorithms. Unfortunately, clean and fully sampled ground-truth data…

Computer Vision and Pattern Recognition · Computer Science 2022-12-05 Hemant Kumar Aggarwal , Aniket Pramanik , Maneesh John , Mathews Jacob

For computer vision applications, prior works have shown the efficacy of reducing the numeric precision of model parameters (network weights) in deep neural networks but also that reducing the precision of activations hurts model accuracy…

Machine Learning · Computer Science 2017-04-12 Asit Mishra , Jeffrey J Cook , Eriko Nurvitadhi , Debbie Marr

Quality feature representation is key to instance image retrieval. To attain it, existing methods usually resort to a deep model pre-trained on benchmark datasets or even fine-tune the model with a task-dependent labelled auxiliary dataset.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Zhongyan Zhang , Lei Wang , Yang Wang , Luping Zhou , Jianjia Zhang , Peng Wang , Fang Chen

The ever-increasing large language models (LLMs), though opening a potential path for the upcoming artificial general intelligence, sadly drops a daunting obstacle on the way towards their on-device deployment. As one of the most…

Artificial Intelligence · Computer Science 2024-02-27 Yuxin Zhang , Lirui Zhao , Mingbao Lin , Yunyun Sun , Yiwu Yao , Xingjia Han , Jared Tanner , Shiwei Liu , Rongrong Ji

Advances in high resolution remote sensing image analysis are currently hampered by the difficulty of gathering enough annotated data for training deep learning methods, giving rise to a variety of small datasets and associated…

Computer Vision and Pattern Recognition · Computer Science 2023-03-08 Dimitri Gominski , Valérie Gouet-Brunet , Liming Chen

Low-Rank Adaptation (LoRA) has significantly advanced parameter-efficient fine-tuning of large pretrained models. LoRA augments the pre-trained weights of a model by adding the product of two smaller matrices that together form a low-rank…

Artificial Intelligence · Computer Science 2025-07-09 David Bensaïd , Noam Rotstein , Roy Velich , Daniel Bensaïd , Ron Kimmel

In the absence of large labelled datasets, self-supervised learning techniques can boost performance by learning useful representations from unlabelled data, which is often more readily available. However, there is often a domain shift…

Machine Learning · Computer Science 2020-06-23 Linus Ericsson , Henry Gouk , Timothy M. Hospedales

Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Samuele Poppi , Sara Sarto , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

Low-Rank Adaptation (LoRA), as a representative Parameter-Efficient Fine-Tuning (PEFT)method, significantly enhances the training efficiency by updating only a small portion of the weights in Large Language Models (LLMs). Recently,…

Computation and Language · Computer Science 2024-09-30 Xijie Huang , Zechun Liu , Shih-Yang Liu , Kwang-Ting Cheng

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads…

Machine Learning · Computer Science 2024-10-21 Chuanyu Tang , Yilong Chen , Zhenyu Zhang , Junyuan Shang , Wenyuan Zhang , Yong Huang , Tingwen Liu

Fine-tuning large language models (LLMs) aims to adapt pre-trained models to specific tasks using relatively small and domain-specific datasets. Among Parameter-Efficient Fine-Tuning (PEFT) methods, Low-Rank Adaptation (LoRA) stands out by…

Computation and Language · Computer Science 2026-04-16 Yarui Cao , Kai Liu

Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are invariant to weight rescaling due to the normalization. In this…

Machine Learning · Computer Science 2022-06-22 Ziquan Liu , Yufei Cui , Jia Wan , Yu Mao , Antoni B. Chan

We propose a new mass-mapping algorithm, specifically designed to recover small-scale information from a combination of gravitational shear and flexion. Including flexion allows us to supplement the shear on small scales in order to…

Cosmology and Nongalactic Astrophysics · Physics 2016-06-08 Francois Lanusse , Jean-Luc Starck , Adrienne Leonard , Sandrine Pires