English
Related papers

Related papers: S2A: A Unified Framework for Parameter and Memory …

200 papers

Parameter-efficient fine-tuning (PEFT) is a popular method for tailoring pre-trained large language models (LLMs), especially as the models' scale and the diversity of tasks increase. Low-rank adaptation (LoRA) is based on the idea that the…

Computation and Language · Computer Science 2025-05-27 Pengjie Ren , Chengshun Shi , Shiguang Wu , Mengqi Zhang , Zhaochun Ren , Maarten de Rijke , Zhumin Chen , Jiahuan Pei

This paper presents ProFL, a new framework that effectively addresses the memory constraints in FL. Rather than updating the full model during local training, ProFL partitions the model into blocks based on its original architecture and…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-22 Yebo Wu , Li Li , Chengzhong Xu

The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require additional training stages to become effective…

Machine Learning · Computer Science 2025-10-24 Jacob L. Block , Sundararajan Srinivasan , Liam Collins , Aryan Mokhtari , Sanjay Shakkottai

A fundamental step in the development of machine learning models commonly involves the tuning of hyperparameters, often leading to multiple model training runs to work out the best-performing configuration. As machine learning tasks and…

Machine Learning · Computer Science 2024-12-12 Daniel Geissler , Bo Zhou , Sungho Suh , Paul Lukowicz

Inductive transfer learning has had a big impact on computer vision and NLP domains but has not been used in the area of recommender systems. Even though there has been a large body of research on generating recommendations based on…

Information Retrieval · Computer Science 2020-06-11 Fajie Yuan , Xiangnan He , Alexandros Karatzoglou , Liguang Zhang

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Many recent studies have focused on fine-tuning pre-trained models for speech emotion recognition (SER), resulting in promising performance compared to traditional methods that rely largely on low-level, knowledge-inspired acoustic…

Sound · Computer Science 2024-02-15 Tiantian Feng , Shrikanth Narayanan

Parameter-efficient fine-tuning (PEFT) is a scalable approach for adapting large speech foundation models to new domains. While methods such as LoRA and its state-of-the-art variants reduce adaptation costs, they typically allocate…

Sound · Computer Science 2026-01-21 Pu Wang , Shinji Watanabe , Hugo Van hamme

Adapting Large Language Models (LLMs) to specialized domains typically incurs high data and computational overhead. While prior efficiency efforts have largely treated data selection and parameter-efficient fine-tuning as isolated…

Machine Learning · Computer Science 2026-05-22 Hao Chen , Qi Zhang , Liyao Li , Zhanming Shen , Wentao Ye , Lirong Gao , Ningtao Wang , Xing Fu , Xiaoyu Shen , Junbo Zhao

Despite the effectiveness of data selection for large language models (LLMs) during pretraining and instruction fine-tuning phases, improving data efficiency in supervised fine-tuning (SFT) for specialized domains poses significant…

Computation and Language · Computer Science 2024-12-06 Yu Yang , Siddhartha Mishra , Jeffrey N Chiang , Baharan Mirzasoleiman

Chart-to-code generation is a critical task in automated data visualization, translating complex chart structures into executable programs. While recent Multi-modal Large Language Models (MLLMs) improve chart representation, existing…

Software Engineering · Computer Science 2025-12-01 Yifei Wang , Jacky Keung , Zhenyu Mao , Jingyu Zhang , Yuchen Cao

Training deep learning models can be computationally expensive. Prior works have shown that increasing the batch size can potentially lead to better overall throughput. However, the batch size is frequently limited by the accelerator memory…

Machine Learning · Computer Science 2023-01-25 Muralidhar Andoorveedu , Zhanda Zhu , Bojian Zheng , Gennady Pekhimenko

Edge-computing requires high-performance energy-efficient embedded systems. Fixed-function or custom accelerators, such as FFT or FIR filter engines, are very efficient at implementing a particular functionality for a given set of…

Hardware Architecture · Computer Science 2022-06-03 Benoît Walter Denkinger , Miguel Peón-Quirós , Mario Konijnenburg , David Atienza , Francky Catthoor

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized…

Despite the growing integration of deep models into mobile terminals, the accuracy of these models declines significantly due to various deployment interferences. Test-time adaptation (TTA) has emerged to improve the performance of deep…

Computer Vision and Pattern Recognition · Computer Science 2025-03-27 Ke Ma , Jiaqi Tang , Bin Guo , Fan Dang , Sicong Liu , Zhui Zhu , Lei Wu , Cheng Fang , Ying-Cong Chen , Zhiwen Yu , Yunhao Liu

Catastrophic forgetting has remained a critical challenge for deep neural networks in Continual Learning (CL) as it undermines consolidated knowledge when learning new tasks. Parameter efficient fine tuning CL techniques are gaining…

Machine Learning · Computer Science 2026-01-27 Prashant Shivaram Bhat , Shakib Yazdani , Elahe Arani , Bahram Zonooz

The rapid increase in the volume of data increased the size and complexity of the deep learning models. These models are now more resource-intensive and time-consuming for training than ever. This paper presents a quantum transfer learning…

Quantum Physics · Physics 2024-09-04 Sounak Bhowmik , Himanshu Thapliyal

In the arena of language model fine-tuning, the traditional approaches, such as Domain-Adaptive Pretraining (DAPT) and Task-Adaptive Pretraining (TAPT), although effective, but computational intensive. This research introduces a novel…

Computation and Language · Computer Science 2024-05-10 Keyu Chen , Yuan Pang , Zi Yang

Training on the Edge enables neural networks to learn continuously from new data after deployment on memory-constrained edge devices. Previous work is mostly concerned with reducing the number of model parameters which is only beneficial…

Machine Learning · Computer Science 2021-11-01 Abdelrahman Hosny , Marina Neseem , Sherief Reda

Low-rank adaptation (LoRA) has been demonstrated effective in reducing the trainable parameter number when fine-tuning a large foundation model (LLM). However, it still encounters computational and memory challenges when scaling to larger…

Computer Vision and Pattern Recognition · Computer Science 2025-02-11 Yixian Shen , Qi Bi , Jia-Hong Huang , Hongyi Zhu , Andy D. Pimentel , Anuj Pathania