English
Related papers

Related papers: Low-Rank Adapters Initialization via Gradient Surg…

200 papers

This paper introduces CURLoRA, a novel approach to fine-tuning large language models (LLMs) that leverages CUR matrix decomposition in the context of Low-Rank Adaptation (LoRA). Our method addresses two critical challenges in LLM…

Machine Learning · Computer Science 2024-08-28 Muhammad Fawi

In this paper, we study the role of initialization in Low Rank Adaptation (LoRA) as originally introduced in Hu et al. (2021). Essentially, to start from the pretrained model as initialization for finetuning, one can either initialize B to…

Machine Learning · Computer Science 2024-06-13 Soufiane Hayou , Nikhil Ghosh , Bin Yu

LoRA (Low-Rank Adaptation) has emerged as a preferred method for efficiently adapting Large Language Models (LLMs) with remarkable simplicity and efficacy. This note extends the original LoRA paper by offering new perspectives that were not…

Machine Learning · Computer Science 2024-04-09 Vlad Fomenko , Han Yu , Jongho Lee , Stanley Hsieh , Weizhu Chen

In many deployed systems (multilingual ASR, cross-hospital imaging, region-specific perception), multiple pretrained specialist models coexist. Yet, new target domains often require domain expansion: a generalized model that performs well…

Machine Learning · Computer Science 2026-01-30 Jong-Ik Park , Shreyas Chaudhari , Srinivasa Pranav , Carlee Joe-Wong , José M. F. Moura

Efficient Visual Instruction Fine-Tuning (EVIT) seeks to adapt Multimodal Large Language Models (MLLMs) to downstream tasks with minimal computational overhead. However, as task diversity and complexity increase, EVIT faces significant…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Pengkun Jiao , Bin Zhu , Jingjing Chen , Chong-Wah Ngo , Yu-Gang Jiang

Parameter Efficient Tuning has been an prominent approach to adapt the Large Language Model to downstream tasks. Most previous works considers adding the dense trainable parameters, where all parameters are used to adapt certain task. We…

Computation and Language · Computer Science 2023-11-16 Yun Zhu , Nevan Wichers , Chu-Cheng Lin , Xinyi Wang , Tianlong Chen , Lei Shu , Han Lu , Canoee Liu , Liangchen Luo , Jindong Chen , Lei Meng

LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data, while…

Machine Learning · Computer Science 2026-04-09 Qingyue Zhang , Chang Chu , Tianren Peng , Qi Li , Xiangyang Luo , Zhihao Jiang , Shao-Lun Huang

Efficient fine-tuning plays a fundamental role in modern large models, with low-rank adaptation emerging as a particularly promising approach. However, the existing variants of LoRA are hampered by limited expressiveness, a tendency to…

Computation and Language · Computer Science 2024-07-02 Siwei Li , Yifan Yang , Yifei Shen , Fangyun Wei , Zongqing Lu , Lili Qiu , Yuqing Yang

Pre-trained large language models (LLMs) often need specialization for domain-specific tasks. Low-Rank Adaptation (LoRA) is a popular approach that adapts a base model to multiple tasks by adding lightweight trainable adapters. In this…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-01-23 Suyi Li , Hanfeng Lu , Tianyuan Wu , Minchen Yu , Qizhen Weng , Xusheng Chen , Yizhou Shan , Binhang Yuan , Wei Wang

Supervised fine-tuning is the most common method to adapt large language models (LLMs) to downstream tasks, but full fine-tuning LLMs requires massive computational resources. Recently, parameter-efficient fine-tuning (PEFT) methods have…

Computation and Language · Computer Science 2024-02-27 Xiangdi Meng , Damai Dai , Weiyao Luo , Zhe Yang , Shaoxiang Wu , Xiaochen Wang , Peiyi Wang , Qingxiu Dong , Liang Chen , Zhifang Sui

Post-training alignment of large language models (LLMs) relies on large-scale human annotations guided by policy specifications that change over time. Cultural shifts, value reinterpretations, and regulatory or industrial updates make…

Computation and Language · Computer Science 2026-05-12 Aakash Sen Sharma , Debdeep Sanyal , Manodeep Ray , Vivek Srivastava , Shirish Karande , Murari Mandal

Large Language Models (LLMs) possess encompassing capabilities that can process diverse language-related tasks. However, finetuning on LLMs will diminish this general skills and continual finetuning will further cause severe degradation on…

Machine Learning · Computer Science 2025-07-09 Kai Tong , Kang Pan , Xiao Zhang , Erli Meng , Run He , Yawen Cui , Nuoyan Guo , Huiping Zhuang

Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by training small…

Information Retrieval · Computer Science 2023-03-24 Vaishali Pal , Carlos Lassance , Hervé Déjean , Stéphane Clinchant

We present a novel initialization technique for the range-aided simultaneous localization and mapping (RA-SLAM) problem. In RA-SLAM we consider measurements of point-to-point distances in addition to measurements of rigid transformations to…

Robotics · Computer Science 2022-10-10 Alan Papalia , Joseph Morales , Kevin J. Doherty , David M. Rosen , John J. Leonard

This paper presents PRIMAL, a processing-in-memory (PIM) based large language model (LLM) inference accelerator with low-rank adaptation (LoRA). PRIMAL integrates heterogeneous PIM processing elements (PEs), interconnected by 2D-mesh…

Hardware Architecture · Computer Science 2026-01-21 Yue Jiet Chong , Yimin Wang , Zhen Wu , Xuanyao Fong

Low-rank adaptation (LoRA) is a widely used parameter-efficient fine-tuning method. In standard LoRA layers, one of the matrices, $A$ or $B$, is initialized to zero, ensuring that fine-tuning starts from the pretrained model. However, there…

Machine Learning · Computer Science 2025-08-19 Shiwei Li , Xiandi Luo , Xing Tang , Haozhao Wang , Hao Chen , Weihong Luo , Yuhua Li , Xiuqiang He , Ruixuan Li

Training data attribution (TDA) identifies which training examples most influenced a model's prediction. Influence function methods are a theoretically grounded family of TDA methods and exploit gradients. To overcome the scalability…

Machine Learning · Computer Science 2026-05-15 Shuangqi Li , Hieu Le , Jingyi Xu , Mathieu Salzmann

Fine-tuning Large Language Models (LLMs) has become a crucial technique for adapting pre-trained models to downstream tasks. However, the enormous size of LLMs poses significant challenges in terms of computational complexity and resource…

Computation and Language · Computer Science 2024-10-28 Yifei Zhang , Hao Zhu , Aiwei Liu , Han Yu , Piotr Koniusz , Irwin King

Accelerator memory and networking constraints have emerged as dominant bottlenecks when training large language models LLMs with billions of parameters. Existing low rank gradient estimators such as GaLoRE and FLORA compress gradients and…

Machine Learning · Computer Science 2025-05-27 Matan Haroush , Daniel Soudry

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Qinhao Zhou , Yuwen Tan , Boqing Gong , Xiang Xiang