English
Related papers

Related papers: Dynamic Base model Shift for Delta Compression

200 papers

We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data. This problem primarily results in a decline in…

Computation and Language · Computer Science 2023-12-13 Ibtihel Amara , Vinija Jain , Aman Chadha

When predicting a target variable $Y$ from features $X$, the prediction $\hat{Y}$ can be performative: an agent might act on this prediction, affecting the value of $Y$ that we eventually observe. Performative predictions are deliberately…

Machine Learning · Computer Science 2024-04-09 Philip Boeken , Onno Zoeter , Joris M. Mooij

Fine-tuning is a promising technique for leveraging Transformer-based language models in downstream tasks. As model sizes continue to grow, updating all model parameters becomes increasingly costly. Parameter-efficient fine-tuning methods…

Computation and Language · Computer Science 2025-06-27 Xiaoshuang Ji , Zhendong Zhao , Xiaojun Chen , Xin Zhao , Zeyao Liu

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…

Computation and Language · Computer Science 2026-03-30 Yijiong Yu , Shuai Yuan , Jie Zheng , Huazheng Wang , Ji Pei

With time, machine learning models have increased in their scope, functionality and size. Consequently, the increased functionality and size of such models requires high-end hardware to both train and provide inference after the fact. This…

Machine Learning · Computer Science 2021-09-07 Arhum Ishtiaq , Sara Mahmood , Maheen Anees , Neha Mumtaz

Diffusion models have recently exhibited remarkable abilities to synthesize striking image samples since the introduction of denoising diffusion probabilistic models (DDPMs). Their key idea is to disrupt images into noise through a fixed…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Zijian Zhang , Zhou Zhao , Jun Yu , Qi Tian

As LLMs continue to scale, improving training efficiency increasingly depends on using data more effectively. Data selection addresses this problem by allocating a limited training budget to samples that best promote a target behavior.…

Machine Learning · Computer Science 2026-05-21 Qihao Lin , Guanxu Chen , Dongrui Liu , Jing Shao

Parameter-efficient fine-tuning methods (PEFTs) offer the promise of adapting large pre-trained models while only tuning a small number of parameters. They have been shown to be competitive with full model fine-tuning for many downstream…

Computation and Language · Computer Science 2022-10-25 Ahmet Üstün , Asa Cooper Stickland

Adapting pre-trained large language models (LLMs) is crucial but challenging due to their enormous size. Parameter-efficient fine-tuning (PEFT) techniques typically employ additive adapters applied to frozen model weights. To further reduce…

Machine Learning · Computer Science 2026-01-05 Tianyi Zhang , Junda Su , Aditya Desai , Oscar Wu , Zhaozhuo Xu , Anshumali Shrivastava

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

Machine Learning · Statistics 2026-02-05 Kazuto Fukuchi , Ryuichiro Hataya , Kota Matsui

Domain shift, characterized by degraded model performance during transition from labeled source domains to unlabeled target domains, poses a persistent challenge for deploying deep learning systems. Current unsupervised domain adaptation…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Zhitong Cheng , Yiran Jiang , Yulong Ge , Yufeng Li , Zhongheng Qin , Rongzhi Lin , Jianwei Ma

Software is constantly changing, requiring developers to perform several derived tasks in a timely manner, such as writing a description for the intention of the code change, or identifying the defect-prone code changes. Considering that…

Software Engineering · Computer Science 2023-05-19 Bo Lin , Shangwen Wang , Zhongxin Liu , Yepang Liu , Xin Xia , Xiaoguang Mao

Currently, machine learning (ML) methods are widely used to process the results of physical experiments. In some cases, due to the limited amount of experimental data, ML-models can be pre-trained on synthetic data simulated based on the…

Computational Physics · Physics 2022-09-22 Y. R. Rodimkov , V. D. Volokitin , I. B. Meyerov , E. S. Efimenko

Dataset Distillation (DD) is a prominent technique that encapsulates knowledge from a large-scale original dataset into a small synthetic dataset for efficient training. Meanwhile, Pre-trained Models (PTMs) function as knowledge…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Yao Lu , Xuguang Chen , Yuchen Zhang , Jianyang Gu , Tianle Zhang , Yifan Zhang , Xiaoniu Yang , Qi Xuan , Kai Wang , Yang You

Deep learning based models are used regularly in every applications nowadays. Generally we train a single model on a single task. However, we can train multiple tasks on a single model under multi-task learning settings. This provides us…

Machine Learning · Computer Science 2023-03-14 Aminul Huq , Mst Tasnim Pervin

Foundational vision transformer models have shown impressive few shot performance on many vision tasks. This research presents a novel investigation into the application of parameter efficient fine-tuning methods within an active learning…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Athmanarayanan Lakshmi Narayanan , Ranganath Krishnan , Amrutha Machireddy , Mahesh Subedar

Large pre-trained models have achieved great success in many natural language processing tasks. However, when they are applied in specific domains, these models suffer from domain shift and bring challenges in fine-tuning and online serving…

Computation and Language · Computer Science 2021-06-30 Yunzhi Yao , Shaohan Huang , Wenhui Wang , Li Dong , Furu Wei

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific…

Computation and Language · Computer Science 2024-12-23 Barry Menglong Yao , Qifan Wang , Lifu Huang

While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to enhance training efficiency and reduce computational costs.…

Machine Learning · Computer Science 2025-07-23 Yang Yu , Kai Han , Hang Zhou , Yehui Tang , Kaiqi Huang , Yunhe Wang , Dacheng Tao

Adapting a pre-trained foundation model on downstream tasks should ensure robustness against distribution shifts without the need to retrain the whole model. Although existing weight interpolation methods are simple yet effective, we argue…

Machine Learning · Computer Science 2025-06-02 Changdae Oh , Yixuan Li , Kyungwoo Song , Sangdoo Yun , Dongyoon Han