English
Related papers

Related papers: Expert Merging: Model Merging with Unsupervised Ex…

200 papers

Merging various task-specific Transformer-based models trained on different tasks into a single unified model can execute all the tasks concurrently. Previous methods, exemplified by task arithmetic, have been proven to be both effective…

Machine Learning · Computer Science 2024-06-10 Anke Tang , Li Shen , Yong Luo , Nan Yin , Lefei Zhang , Dacheng Tao

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

Model merging aims to integrate the strengths of multiple fine-tuned models into a unified model while preserving task-specific capabilities. Existing methods, represented by task arithmetic, are typically classified into global- and…

Machine Learning · Computer Science 2025-06-17 Kunda Yan , Min Zhang , Sen Cui , Zikun Qu , Bo Jiang , Feng Liu , Changshui Zhang

While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable the direct integration of multiple models, each fine-tuned…

Computer Vision and Pattern Recognition · Computer Science 2024-10-04 Guodong Du , Junlin Lee , Jing Li , Runhua Jiang , Yifei Guo , Shuyang Yu , Hanting Liu , Sim Kuan Goh , Ho-Kin Tang , Daojing He , Min Zhang

Vision-Language Models (VLMs) combine visual perception with the general capabilities, such as reasoning, of Large Language Models (LLMs). However, the mechanisms by which these two abilities can be combined and contribute remain poorly…

Computation and Language · Computer Science 2025-07-16 Shiqi Chen , Jinghan Zhang , Tongyao Zhu , Wei Liu , Siyang Gao , Miao Xiong , Manling Li , Junxian He

Large Language Models (LLMs) have shown great promise in multilingual machine translation (MT), even with limited bilingual supervision. However, fine-tuning LLMs with parallel corpora presents major challenges, namely parameter…

Computation and Language · Computer Science 2026-05-26 Bo Li , Tianyu Dong , Shaolin Zhu , Deyi Xiong

Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…

Computation and Language · Computer Science 2024-06-19 Guodong Du , Jing Li , Hanting Liu , Runhua Jiang , Shuyang Yu , Yifei Guo , Sim Kuan Goh , Ho-Kin Tang

Data augmentation is a widely used strategy to improve model robustness and generalization by enriching training datasets with synthetic examples. While large language models (LLMs) have demonstrated strong generative capabilities for this…

Machine Learning · Computer Science 2025-09-29 Dongkyu Cho , Miao Zhang , Rumi Chunara

We observe that incorporating a shared layer in a mixture-of-experts can lead to performance degradation. This leads us to hypothesize that learning shared features poses challenges in deep learning, potentially caused by the same feature…

Machine Learning · Computer Science 2024-05-21 Sejik Park

We present Branch-Train-Merge (BTM), a communication-efficient algorithm for embarrassingly parallel training of large language models (LLMs). We show it is possible to independently train subparts of a new class of LLMs on different…

Computation and Language · Computer Science 2022-08-08 Margaret Li , Suchin Gururangan , Tim Dettmers , Mike Lewis , Tim Althoff , Noah A. Smith , Luke Zettlemoyer

Optimizing data mixtures is essential for unlocking the full potential of large language models (LLMs), yet identifying the optimal composition remains computationally prohibitive due to reliance on heuristic trials or expensive proxy…

Machine Learning · Computer Science 2026-01-27 Jiapeng Wang , Changxin Tian , Kunlong Chen , Ziqi Liu , Jiaxin Mao , Wayne Xin Zhao , Zhiqiang Zhang , Jun Zhou

Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While…

Computation and Language · Computer Science 2025-02-20 Shuqi Liu , Han Wu , Bowei He , Xiongwei Han , Mingxuan Yuan , Linqi Song

Reasoning capabilities are crucial for Large Language Models (LLMs), yet a notable gap exists between English and non-English languages. To bridge this disparity, some works fine-tune LLMs to relearn reasoning capabilities in non-English…

Computation and Language · Computer Science 2024-05-28 Zixian Huang , Wenhao Zhu , Gong Cheng , Lei Li , Fei Yuan

The integration of Federated Learning (FL) and Mixture-of-Experts (MoE) presents a compelling pathway for training more powerful, large-scale artificial intelligence models (LAMs) on decentralized data while preserving privacy. However,…

Machine Learning · Computer Science 2025-07-09 Xiaobing Chen , Boyang Zhang , Xiangwei Zhou , Mingxuan Sun , Shuai Zhang , Songyang Zhang , Geoffrey Ye Li

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on…

Machine Learning · Computer Science 2026-05-29 Bethan Evans , Benjamin Etheridge , Stephen Roberts , Jared Tanner

Model merging enables powerful capabilities in neural networks without requiring additional training. In this paper, we introduce a novel perspective on model merging by leveraging the fundamental mechanisms of neural network…

Machine Learning · Computer Science 2025-09-19 Haiquan Qiu , You Wu , Dong Li , Jianmin Guo , Quanming Yao

Mixture-of-Experts (MoE) language models organize knowledge into explicitly routed expert modules, making expert-level representations traceable and analyzable. By analyzing expert activation patterns in MoE large language models (LLMs), we…

Computation and Language · Computer Science 2026-05-12 Chang Liu , Boyu Shi , Xu Yang , Xin Geng

The goal of this paper is to improve (upcycle) an existing large language model without the prohibitive requirements of continued pre-training of the full-model. The idea is to split the pre-training data into semantically relevant groups…

Machine Learning · Computer Science 2024-10-15 Ajinkya Tejankar , KL Navaneet , Ujjawal Panchal , Kossar Pourahmadi , Hamed Pirsiavash

Competency modeling is widely used in human resource management to select, develop, and evaluate talent. However, traditional expert-driven approaches rely heavily on manual analysis of large volumes of interview transcripts, making them…

Computation and Language · Computer Science 2026-02-16 Silin Du , Manqing Xin , Raymond Jia Wang

In this paper, we introduce a novel weighted co-training approach that is guided by Large Language Models (LLMs). Namely, in our co-training approach, we use LLM labels on unlabeled data as target labels and co-train two encoder-only based…

Machine Learning · Computer Science 2025-09-24 Md Mezbaur Rahman , Cornelia Caragea
‹ Prev 1 3 4 5 6 7 10 Next ›