English
Related papers

Related papers: Mixture of LoRA Experts

200 papers

While large language models (LLMs) excel on generation tasks, their decoder-only architecture often limits their potential as embedding models if no further representation finetuning is applied. Does this contradict their claim of…

Computation and Language · Computer Science 2024-10-17 Ziyue Li , Tianyi Zhou

Fine-tuning is a crucial paradigm for adapting pre-trained large language models to downstream tasks. Recently, methods like Low-Rank Adaptation (LoRA) have been shown to effectively fine-tune LLMs with an extreme reduction in trainable…

Machine Learning · Computer Science 2025-10-23 Reece Shuttleworth , Jacob Andreas , Antonio Torralba , Pratyusha Sharma

Although many efforts have been made, it is still a challenge to balance the training budget, downstream performance, and the general capabilities of the LLMs in many applications. Training the whole model for downstream tasks is expensive,…

Machine Learning · Computer Science 2025-01-29 Jiayi Han , Liang Du , Hongwei Du , Xiangguo Zhou , Yiwen Wu , Weibo Zheng , Donghong Han

Large Language Models (LLMs) have achieved remarkable progress, with Parameter-Efficient Fine-Tuning (PEFT) emerging as a key technique for downstream task adaptation. However, existing PEFT methods mainly operate in Euclidean space,…

Machine Learning · Computer Science 2026-02-17 Buze Zhang , Jinkai Tao , Zilang Zeng , Neil He , Ali Maatouk , Menglin Yang , Rex Ying

In this paper, we introduce a method for fine-tuning Large Language Models (LLMs), inspired by Multi-Task learning in a federated manner. Our approach leverages the structure of each client's model and enables a learning scheme that…

Machine Learning · Computer Science 2024-10-22 Ahmed Elbakary , Chaouki Ben Issaid , Tamer ElBatt , Karim Seddik , Mehdi Bennis

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Machine Learning · Computer Science 2026-02-09 Haiyun Qiu , Xingyu Wu , Liang Feng , Kay Chen Tan

As the capabilities of large language models (LLMs) continue to expand, aligning these models with human values remains a significant challenge. Recent studies show that reasoning abilities contribute significantly to model safety, while…

Computation and Language · Computer Science 2025-06-03 Zhili Liu , Yunhao Gou , Kai Chen , Lanqing Hong , Jiahui Gao , Fei Mi , Yu Zhang , Zhenguo Li , Xin Jiang , Qun Liu , James T. Kwok

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants…

Machine Learning · Computer Science 2025-10-24 Heming Zou , Yunliang Zang , Wutong Xu , Yao Zhu , Xiangyang Ji

Parameter-efficient fine-tuning methods, such as LoRA, offer a practical way to adapt large vision and language models to client tasks. However, this becomes particularly challenging under task-level heterogeneity in federated deployments.…

Machine Learning · Computer Science 2026-02-24 Yinan Zou , Md Kamran Chowdhury Shisher , Christopher G. Brinton , Vishrant Tripathi

As FMs drive progress toward Artificial General Intelligence (AGI), fine-tuning them under privacy and resource constraints has become increasingly critical particularly when highquality training data resides on distributed edge devices.…

Machine Learning · Computer Science 2025-08-27 Gang Hu , Yinglei Teng , Pengfei Wu , Nan Wang

Low-Rank Adaptation (LoRA) has emerged as a popular technique for fine-tuning large language models (LLMs) to various domains due to its modular design and widespread availability on platforms like Huggingface. This modularity has sparked…

Machine Learning · Computer Science 2025-02-17 Ziyu Zhao , Tao Shen , Didi Zhu , Zexi Li , Jing Su , Xuwu Wang , Kun Kuang , Fei Wu

Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks. Increasing instruction data substantially is a direct…

Computation and Language · Computer Science 2024-03-11 Shihan Dou , Enyu Zhou , Yan Liu , Songyang Gao , Jun Zhao , Wei Shen , Yuhao Zhou , Zhiheng Xi , Xiao Wang , Xiaoran Fan , Shiliang Pu , Jiang Zhu , Rui Zheng , Tao Gui , Qi Zhang , Xuanjing Huang

The Mixture of Experts (MoE) paradigm has been successfully integrated into Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning (PEFT), delivering performance gains with minimal parameter overhead. However, a key limitation of…

Computation and Language · Computer Science 2025-09-26 Jiayi Han , Liang Du , Yinda Chen , Xiao Kang , Weiyang Ding , Donghong Han

Mixture-of-Experts (MoE) approaches have recently gained traction in robotics applications due to their ability to dynamically allocate computational resources and specialize sub-networks for distinct tasks or environmental contexts,…

Robotics · Computer Science 2026-02-18 Dmytro Kuzmenko , Nadiya Shvai

Low-Rank Adaptation (LoRA) dominates parameter-efficient fine-tuning of large language models, yet most variants target dense architectures. Mixture-of-Experts (MoE) models scale parameters at near-constant per-token compute, and their…

Machine Learning · Computer Science 2026-05-20 Jia Wei , Zhonghao Zhang , Ping Chen , Qianyang li , Yancheng Pan , Shaoxun Wang , Ziyi Qiu , Longxiang Wang

Mixture of Experts (MoE) LLMs face significant obstacles due to their massive parameter scale, which imposes memory, storage, and deployment challenges. Although recent expert merging methods promise greater efficiency by consolidating…

Machine Learning · Computer Science 2025-07-01 Lujun Li , Zhu Qiyuan , Jiacheng Wang , Wei Li , Hao Gu , Sirui Han , Yike Guo

Large language models (LLMs) excel in complex tasks through advanced prompting techniques like Chain-of-Thought (CoT) and Tree-of-Thought (ToT), but their reliance on manually crafted, task-specific prompts limits adaptability and…

Computation and Language · Computer Science 2025-07-04 Tao Xiong , Xavier Hu , Wenyan Fan , Shengyu Zhang

The performance of the reward model (RM) is a critical factor in improving the effectiveness of the large language model (LLM) during alignment fine-tuning. There remain two challenges in RM training: 1) training the same RM using various…

Computation and Language · Computer Science 2024-04-30 Shanghaoran Quan

Existing resource-adaptive LoRA federated fine-tuning methods enable clients to fine-tune models using compressed versions of global LoRA matrices, in order to accommodate various compute resources across clients. This compression…

Machine Learning · Computer Science 2025-07-16 Khiem Le , Tuan Tran , Ting Hua , Nitesh V. Chawla

Merging or routing low-rank adapters (LoRAs) has emerged as a popular solution for enhancing large language models, particularly when data access is restricted by regulatory or domain-specific constraints. This position paper argues that…

Computation and Language · Computer Science 2025-06-17 Mei-Yen Chen , Thi Thu Uyen Hoang , Michael Hahn , M. Saquib Sarfraz
‹ Prev 1 4 5 6 7 8 10 Next ›