English
Related papers

Related papers: Gradient-Based LoRA Rank Allocation Under GRPO: An…

200 papers

We study the \textit{parameter placement problem}: given a fixed budget of $k$ trainable entries within the B matrix of a LoRA adapter (A frozen), does the choice of which $k$ matter? Under supervised fine-tuning, random and informed…

Machine Learning · Computer Science 2026-05-13 Arijit Sehanobish , Charles Lovering

Low-Rank Adaptation (LoRA) is a popular method for parameter-efficient fine-tuning (PEFT) of generative models, valued for its simplicity and effectiveness. Despite recent enhancements, LoRA still suffers from a fundamental limitation:…

Machine Learning · Computer Science 2026-01-16 Yeonjoon Jung , Daehyun Ahn , Hyungjun Kim , Taesu Kim , Eunhyeok Park

Low-Rank Adaptation (LoRA) is a crucial method for efficiently fine-tuning large language models (LLMs), with its effectiveness influenced by two key factors: rank selection and weight initialization. While numerous LoRA variants have been…

Machine Learning · Computer Science 2025-10-27 Haonan He , Peng Ye , Yuchen Ren , Yuan Yuan , Luyang Zhou , Shucun Ju , Lei Chen

As large language models (LLMs) scale to billions of parameters, full-parameter fine-tuning becomes compute- and memory-prohibitive. Parameter-efficient fine-tuning (PEFT) mitigates this issue by updating only a small set of task-specific…

Machine Learning · Computer Science 2026-03-17 Xuan Cui , Huiyue Li , Run Zeng , Yunfei Zhao , Jinrui Qian , Wei Duan , Bo Liu , Zhanpeng Zhou

Low-Rank Adaptation (LoRA) has proven effective in reducing computational costs while maintaining performance comparable to fully fine-tuned foundation models across various tasks. However, its fixed low-rank structure restricts its…

Computer Vision and Pattern Recognition · Computer Science 2025-07-02 Chuyan Zhang , Kefan Wang , Yun Gu

Low-rank adaptation (LoRA) assigns a uniform rank to every adapted weight matrix - a practical convenience that ignores a fundamental reality: different layers contribute unequally to task adaptation. We address this with a lightweight…

Machine Learning · Computer Science 2026-05-19 Ramakrishnan Sathyavageeswaran

Parameter-efficient fine-tuning (PEFT) is widely studied for its effectiveness and efficiency in the era of large language models. Low-rank adaptation (LoRA) has demonstrated commendable performance as a popular and representative method.…

Computation and Language · Computer Science 2024-04-16 Zequan Liu , Jiawen Lyn , Wei Zhu , Xing Tian , Yvette Graham

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Machine Learning · Computer Science 2026-04-24 Bingcong Li , Yilang Zhang , Georgios B. Giannakis

Post-training alignment has produced dozens of competing algorithms -- DPO, SimPO, KTO, GRPO, and others -- yet practitioners lack controlled comparisons to guide algorithm selection. We present OXRL, a unified framework implementing 51…

Machine Learning · Computer Science 2026-03-23 Xiaoyi Li

As large language models (LLMs) have become increasingly compute and memory intensive, parameter-efficient fine-tuning (PEFT) methods are now a common strategy to fine-tune LLMs. A popular PEFT method is Low-Rank Adapters (LoRA), which adds…

Computation and Language · Computer Science 2023-12-08 Damjan Kalajdzievski

The enhancement of reasoning capabilities in large language models (LLMs) has garnered significant attention, with supervised fine-tuning (SFT) and reinforcement learning emerging as dominant paradigms. While recent studies recognize the…

Artificial Intelligence · Computer Science 2026-03-17 Zhijie Wang

RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across diverse tasks. A straightforward multi-task adaptation of…

With the proliferation of large pre-trained language models (PLMs), fine-tuning all model parameters becomes increasingly inefficient, particularly when dealing with numerous downstream tasks that entail substantial training and storage…

Computation and Language · Computer Science 2024-01-23 Nadav Benedek , Lior Wolf

Large language models are increasingly adapted to downstream tasks through fine-tuning. Full supervised fine-tuning (SFT) and parameter-efficient fine-tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), are two dominant approaches.…

Computation and Language · Computer Science 2025-12-18 Darshita Rathore , Vineet Kumar , Chetna Bansal , Anindya Moitra

Large Language Models (LLMs) have transformed both everyday life and scientific research. However, adapting LLMs from general-purpose models to specialized tasks remains challenging, particularly in resource-constrained environments.…

Machine Learning · Computer Science 2025-09-12 Hao Zhang , Bo Huang , Zhenjia Li , Xi Xiao , Hui Yi Leong , Zumeng Zhang , Xinwei Long , Tianyang Wang , Hao Xu

Group Relative Policy Optimization (GRPO) is a standard algorithm for reinforcement learning from verifiable rewards, but its group-mean-centered advantage can fail under binary rewards. The failure mode is gradient starvation: when every…

Machine Learning · Computer Science 2026-05-11 Wenhua Nie , Jianan Wu , Junlin Liu , Ziwei Li , Zheng Lin , Zhang Zijian , Yilong Fan , Haoran Zheng , Jyh-Shing Roger Jang

Alignment methodologies have emerged as a critical pathway for enhancing language model alignment capabilities. While SFT (supervised fine-tuning) accelerates convergence through direct token-level loss intervention, its efficacy is…

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and…

Machine Learning · Computer Science 2026-02-02 Cheng Ge , Caitlyn Heqi Yin , Hao Liang , Jiawei Zhang

Group Relative Policy Optimization (GRPO) is highly effective for post-training autoregressive (AR) language models, yet its direct application to diffusion large language models (dLLMs) often triggers reward collapse. We identify two…

Machine Learning · Computer Science 2026-03-10 Jianyuan Zhong , Kaibo Wang , Ding Ding , Zijin Feng , Haoli Bai , Yang Xiang , Jiacheng Sun , Qiang Xu

Fine-tuning large-scale pre-trained models is prohibitively expensive in terms of computation and memory costs. Low-Rank Adaptation (LoRA), a popular Parameter-Efficient Fine-Tuning (PEFT) method, offers an efficient solution by optimizing…

Machine Learning · Computer Science 2025-05-27 Tao Li , Zhengbao He , Yujun Li , Yasheng Wang , Lifeng Shang , Xiaolin Huang
‹ Prev 1 2 3 10 Next ›