English
Related papers

Related papers: Chart2Code-MoLA: Efficient Multi-Modal Code Genera…

200 papers

Large language models (LLMs) achieve remarkable performance on diverse downstream and domain-specific tasks via parameter-efficient fine-tuning (PEFT). However, existing PEFT methods, particularly MoE-LoRA architectures, suffer from limited…

Computation and Language · Computer Science 2026-03-03 Jie Cao , Zhenxuan Fan , Zhuonan Wang , Tianwei Lin , Ziyuan Zhao , Rolan Yan , Wenqiao Zhang , Feifei Shao , Hongwei Wang , Jun Xiao , Siliang Tang

Mixture of Experts (MoE) has become a key architectural paradigm for efficiently scaling Large Language Models (LLMs) by selectively activating a subset of parameters for each input token. However, standard MoE architectures face…

Machine Learning · Computer Science 2025-05-27 Zehua Liu , Han Wu , Ruifeng She , Xiaojin Fu , Xiongwei Han , Tao Zhong , Mingxuan Yuan

Being able to effectively read scientific plots, or chart understanding, is a central part toward building effective agents for science. However, existing multimodal large language models (MLLMs), especially open-source ones, are still…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Yuwei Yang , Zeyu Zhang , Yunzhong Hou , Zhuowan Li , Gaowen Liu , Ali Payani , Yuan-Sen Ting , Liang Zheng

This paper introduces a method for adapting LoRA adapters in smaller-sized language models to arbitrary downstream tasks. Unlike standard mixture-of-expert architectures, our method employs a gradient-free routing function to choose a…

Computation and Language · Computer Science 2023-12-04 Joshua Belofsky

Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and styles, in multi-concept image generation. However, current…

Computer Vision and Pattern Recognition · Computer Science 2025-02-10 Xiandong Zou , Mingzhu Shen , Christos-Savvas Bouganis , Yiren Zhao

Large language models (LLMs) have demonstrated remarkable capabilities in various domains, particularly in system 1 tasks, yet the intricacies of their problem-solving mechanisms in system 2 tasks are not sufficiently explored. Recent…

Artificial Intelligence · Computer Science 2025-02-19 Kounianhua Du , Hanjing Wang , Jianxing Liu , Jizheng Chen , Xinyi Dai , Yasheng Wang , Ruiming Tang , Yong Yu , Jun Wang , Weinan Zhang

Parameter-efficient fine-tuning techniques like Low-Rank Adaptation (LoRA) have revolutionized the adaptation of large language models (LLMs) to diverse tasks. Recent efforts have explored mixtures of LoRA modules for multi-task settings.…

Computation and Language · Computer Science 2024-08-06 Lin Ning , Harsh Lara , Meiqi Guo , Abhinav Rastogi

Chart-to-code generation demands strict visual precision and syntactic correctness from Vision-Language Models (VLMs). However, existing approaches are fundamentally constrained by data-centric limitations: despite the availability of…

Computer Vision and Pattern Recognition · Computer Science 2026-04-27 Xiangxi Zheng , Kuang He , Jiayi Hu , Ping Yu , Rui Yan , Yuan Yao , Peng Hou , Anxiang Zeng , Alex Jinpeng Wang

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Machine Learning · Computer Science 2025-07-15 Seokmin Ko

Parameter-efficient finetuning (PEFT) methods effectively adapt large language models (LLMs) to diverse downstream tasks, reducing storage and GPU memory demands. Despite these advantages, several applications pose new challenges to PEFT…

Machine Learning · Computer Science 2024-11-05 Baohao Liao , Christof Monz

We present MoE-MLA-RoPE, a novel architecture combination that combines Mixture of Experts (MoE) with Multi-head Latent Attention (MLA) and Rotary Position Embeddings (RoPE) for efficient language modeling. Our approach addresses the…

Artificial Intelligence · Computer Science 2025-08-05 Sushant Mehta , Raj Dandekar , Rajat Dandekar , Sreedath Panat

Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. However, their performance is limited by the small number of…

Computation and Language · Computer Science 2025-09-23 Hengyuan Zhang , Xinrong Chen , Yingmin Qiu , Xiao Liang , Ziyue Li , Guanyu Wang , Weiping Li , Tong Mo , Hayden Kwok-Hay So , Ngai Wong

Adapting large language models (LLMs) to new domains/tasks and enabling them to be efficient lifelong learners is a pivotal challenge. In this paper, we propose MoRAL, i.e., Mixture-of-Experts augmented Low-Rank Adaptation for Lifelong…

Computation and Language · Computer Science 2024-02-20 Shu Yang , Muhammad Asif Ali , Cheng-Long Wang , Lijie Hu , Di Wang

Parameter-Efficient Fine-Tuning (PEFT) techniques, particularly Low-Rank Adaptation (LoRA), have become essential for adapting Large Language Models (LLMs) to downstream tasks. While the recent FlyLoRA framework successfully leverages…

Machine Learning · Computer Science 2026-03-16 Yuxin Yang , Haoran Zhang , Mingxuan Li , Jiachen Xu , Ruoxi Shen , Zhenyu Wang , Tianhao Liu , Siqi Chen , Weilin Huang

As the key component in multimodal large language models (MLLMs), the ability of the visual encoder greatly affects MLLM's understanding on diverse image content. Although some large-scale pretrained vision encoders such as vision encoders…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Zhuofan Zong , Bingqi Ma , Dazhong Shen , Guanglu Song , Hao Shao , Dongzhi Jiang , Hongsheng Li , Yu Liu

Multimodal Continual Instruction Tuning (MCIT) aims to finetune Multimodal Large Language Models (MLLMs) to continually align with human intent across sequential tasks. Existing approaches often rely on the Mixture-of-Experts (MoE) LoRA…

Computation and Language · Computer Science 2025-06-04 Duzhen Zhang , Yong Ren , Zhong-Zhi Li , Yahan Yu , Jiahua Dong , Chenxing Li , Zhilong Ji , Jinfeng Bai

Low-Rank Adaptation (LoRA) drives research to align its performance with full fine-tuning. However, significant challenges remain: (1) Simply increasing the rank size of LoRA does not effectively capture high-rank information, which leads…

Machine Learning · Computer Science 2024-10-21 Chuanyu Tang , Yilong Chen , Zhenyu Zhang , Junyuan Shang , Wenyuan Zhang , Yong Huang , Tingwen Liu

In fine-tuning large language models (LLMs), conserving computational resources while maintaining effectiveness and improving outcomes within the same computational constraints is crucial. The Low-Rank Adaptation (LoRA) strategy balances…

Machine Learning · Computer Science 2024-09-05 Xiaojun Xiao , Sen Shen , Qiming Bao , Hongfei Rong , Kairui Liu , Zhongsheng Wang , Jiamou Liu

Standard LoRA fine-tuning of Mixture-of-Experts (MoE) models applies adapters to every expert, yet our profiling shows that per-layer expert routing is highly skewed: a small subset of experts handles most tokens in each layer, while many…

Machine Learning · Computer Science 2026-03-26 Andrea Manzoni

The Mixture of Experts (MoE) architecture has emerged as a key technique for scaling Large Language Models by activating only a subset of experts per query. Deploying MoE on consumer-grade edge hardware, however, is constrained by limited…

Artificial Intelligence · Computer Science 2026-05-05 Guoying Zhu , Meng Li , Haipeng Dai , Xuechen Liu , Weijun Wang , Keran Li , Jun xiao , Ligeng Chen , Wei Wang