English
Related papers

Related papers: Vertical LoRA: Dense Expectation-Maximization Inte…

200 papers

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

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient method for fine-tuning Large Langauge Models. It updates the weight matrix as $W=W_0+sBA$, where $W_0$ is the original frozen weight, $s$ is a scaling factor and $A$,$B$ are…

Machine Learning · Computer Science 2026-03-06 Yize Wu , Ke Gao , Ling Li , Yanjun Wu

As large language models (LLMs) continue to scale in size, the computational overhead has become a major bottleneck for task-specific fine-tuning. While low-rank adaptation (LoRA) effectively curtails this cost by confining the weight…

Machine Learning · Computer Science 2026-05-15 Yilang Zhang , Xiaodong Yang , Yiwei Cai , Georgios B. Giannakis

Addressing the resource waste caused by fixed computation paradigms in deep learning models under dynamic scenarios, this paper proposes a Transformer$^{-1}$ architecture based on the principle of deep adaptivity. This architecture achieves…

Machine Learning · Computer Science 2025-01-29 Lumen AI , Tengzhou No. 1 Middle School , Shihao Ji , Zihui Song , Fucheng Zhong , Jisen Jia , Zhaobo Wu , Zheyi Cao , Xu Tianhao

Transformer-based large language models (LLMs) are comprised of billions of parameters arranged in deep and wide computational graphs. Several studies on LLM efficiency optimization argue that it is possible to prune a significant portion…

Computation and Language · Computer Science 2026-04-16 Corentin Kervadec , Iuliia Lysova , Marco Baroni , Gemma Boleda

Transformer-based, pre-trained large language models (LLMs) have demonstrated outstanding performance across diverse domains, particularly in the emerging {\em pretrain-then-finetune} paradigm. Low-Rank Adaptation (LoRA), a…

Machine Learning · Computer Science 2024-09-19 Zhengmao Ye , Dengchun Li , Zetao Hu , Tingfeng Lan , Jian Sha , Sicong Zhang , Lei Duan , Jie Zuo , Hui Lu , Yuanchun Zhou , Mingjie Tang

This study identifies that visual-related functional decoding is distributed across different decoder layers in Multimodal Large Language Models (MLLMs). Typically, each function, such as counting, grounding, or OCR recognition, narrows…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Cheng Shi , Yizhou Yu , Sibei Yang

We introduce MSLoRA, a backbone-agnostic, parameter-efficient adapter that reweights feature responses rather than re-tuning the underlying backbone. Existing low-rank adaptation methods are mostly confined to vision transformers (ViTs) and…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Xu Yang , Gady Agam

Efficiently updating Large Language Models (LLMs) with new or evolving factual knowledge remains a central challenge, as even parameter-efficient adaptation can erode previously acquired reasoning abilities. This tension reflects a…

Artificial Intelligence · Computer Science 2026-05-26 Mustafa Hayri Bilgin , Mariam Barry , Albert Bifet , Azzedine Idir Ait Said , Soumya Banerjee

Low-rank adaptation (LoRA) has been widely adopted as a parameter-efficient technique for fine-tuning large-scale pre-trained models. However, it still lags behind full fine-tuning in performance, partly due to its insufficient exploitation…

Machine Learning · Computer Science 2026-04-03 Zhizhong Li , Sina Sajadmanesh , Jingtao Li , Lingjuan Lyu

As the number of model parameters increases, parameter-efficient fine-tuning (PEFT) has become the go-to choice for tailoring pre-trained large language models. Low-rank Adaptation (LoRA) uses a low-rank update method to simulate full…

Computation and Language · Computer Science 2026-01-13 Yongkang Liu , Xing Li , Mengjie Zhao , Shanru Zhang , Zijing Wang , Qian Li , Shi Feng , Feiliang Ren , Daling Wang , Hinrich Schütze

Vision-language-action (VLA) models have shown strong generalization across tasks and embodiments; however, their reliance on large-scale human demonstrations limits their scalability owing to the cost and effort of manual data collection.…

Robotics · Computer Science 2025-09-30 Rushuai Yang , Hangxing Wei , Ran Zhang , Zhiyuan Feng , Xiaoyu Chen , Tong Li , Chuheng Zhang , Li Zhao , Jiang Bian , Xiu Su , Yi Chen

Continual learning for pre-trained vision-language models requires balancing three competing objectives: retaining pre-trained knowledge, preserving knowledge from a sequence of learned tasks, and maintaining the plasticity to acquire new…

Computer Vision and Pattern Recognition · Computer Science 2026-01-28 Mao-Lin Luo , Zi-Hao Zhou , Yi-Lin Zhang , Yuanyu Wan , Tong Wei , Min-Ling Zhang

Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical application of…

Computation and Language · Computer Science 2024-06-27 Yulong Mao , Kaiyu Huang , Changhao Guan , Ganglin Bao , Fengran Mo , Jinan Xu

Continual machine unlearning aims to remove the influence of data that should no longer be retained, while preserving the usefulness of the model on everything else. This setting becomes especially difficult when deletion requests arrive…

Machine Learning · Computer Science 2026-04-15 Yogachandran Rahulamathavan , Nasir Iqbal , Juncheng Hu , Sangarapillai Lambotharan

Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition,…

Computer Vision and Pattern Recognition · Computer Science 2024-12-12 Sinan Du , Guosheng Zhang , Keyao Wang , Yuanrui Wang , Haixiao Yue , Gang Zhang , Errui Ding , Jingdong Wang , Zhengzhuo Xu , Chun Yuan

How many of a neural network's parameters actually encode task-specific information? We investigate this question with LottaLoRA, a training paradigm in which every backbone weight is drawn at random and frozen; only low-rank LoRA adapters…

Machine Learning · Computer Science 2026-04-14 Hananel Hazan , Yanbo Zhang , Benedikt Hartl , Michael Levin

Vision-Language-Action Models (VLAs) have shown remarkable progress towards embodied intelligence. While their architecture partially resembles that of Large Language Models (LLMs), VLAs exhibit higher complexity due to their multi-modal…

Robotics · Computer Science 2026-03-06 Hugo Buurmeijer , Carmen Amo Alonso , Aiden Swann , Marco Pavone

Fine-tuning pre-trained large language models in a parameter-efficient manner is widely studied for its effectiveness and efficiency. LoRA is one of the most widely used methods, which assumes that the optimization process is essentially…

Computation and Language · Computer Science 2024-12-16 Changqun Li , Chaofan Ding , Kexin Luan , Xinhan Di

Low-Rank Adaptation (LoRA) has recently gained attention for fine-tuning foundation models by incorporating trainable low-rank matrices, thereby reducing the number of trainable parameters. While LoRA offers numerous advantages, its…

Machine Learning · Computer Science 2024-04-29 Yeming Wen , Swarat Chaudhuri
‹ Prev 1 8 9 10 Next ›