English
Related papers

Related papers: Subspace-Boosted Model Merging

200 papers

Model merging has recently gained attention as an economical and scalable approach to incorporate task-specific weights from various tasks into a unified multi-task model. For example, in Task Arithmetic (TA), adding the fine-tuned weights…

Machine Learning · Computer Science 2025-01-10 Feng Xiong , Runxi Cheng , Wang Chen , Zhanqiu Zhang , Yiwen Guo , Chun Yuan , Ruifeng Xu

Dense embeddings are fundamental to modern machine learning systems, powering Retrieval-Augmented Generation (RAG), information retrieval, and representation learning. While instruction-conditioning has become the dominant approach for…

Machine Learning · Computer Science 2025-06-24 Miguel Romero , Shuoyang Ding , Corey D. Barret , Georgiana Dinu , George Karypis

Model merging has emerged as a promising technique for enhancing large language models, though its application in large-scale pre-training remains relatively unexplored. In this paper, we present a comprehensive investigation of model…

Learning high-quality feature embeddings efficiently and effectively is critical for the performance of web-scale machine learning systems. A typical model ingests hundreds of features with vocabularies on the order of millions to billions…

Machine Learning · Computer Science 2024-06-19 Benjamin Coleman , Wang-Cheng Kang , Matthew Fahrbach , Ruoxi Wang , Lichan Hong , Ed H. Chi , Derek Zhiyuan Cheng

Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental trade-off: strong load balancing can suppress expert specialization, while aggressive…

Machine Learning · Computer Science 2026-05-12 Gleb Molodtsov , Alexander Miasnikov , Aleksandr Beznosikov

While machine learning has emerged in recent years as a useful tool for rapid prediction of materials properties, generating sufficient data to reliably train models without overfitting is still impractical for many applications. Towards…

Materials Science · Physics 2022-07-29 Rees Chang , Yu-Xiong Wang , Elif Ertekin

Large language models, such as ChatGPT, Claude, or LLaMA, are gigantic, monolithic, and possess the superpower to simultaneously support thousands of tasks. However, high-throughput applications often prefer smaller task-specific models…

Computation and Language · Computer Science 2025-02-17 Haoyu Yang , Zheng Zhang , Saket Sathe

Scaling the size of language models usually leads to remarkable advancements in NLP tasks. But it often comes with a price of growing computational cost. Although a sparse Mixture of Experts (MoE) can reduce the cost by activating a small…

Computation and Language · Computer Science 2023-11-23 Shwai He , Run-Ze Fan , Liang Ding , Li Shen , Tianyi Zhou , Dacheng Tao

Fine-tuning large language models (LMs) for individual tasks yields strong performance but is expensive for deployment and storage. Recent works explore model merging to combine multiple task-specific models into a single multi-task model…

Computation and Language · Computer Science 2025-05-30 Haobo Zhang , Jiayu Zhou

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine Learning · Computer Science 2026-05-12 Xi Wang , Cheng Deng

Recent advances in deep learning have led to a surge of open-source models across diverse domains. While model merging offers a promising way to combine their strengths, existing approaches often suffer from parameter conflicts that degrade…

Machine Learning · Computer Science 2025-10-28 Yunfei Liang

Model merging seeks to integrate task-specific expert models into a unified architecture while preserving multi-task generalization capabilities, yet parameter interference between constituent models frequently induces performance…

Machine Learning · Computer Science 2025-06-12 Runxi Cheng , Feng Xiong , Yongxian Wei , Wanyun Zhu , Chun Yuan

Traditional models grounded in first principles often struggle with accuracy as the system's complexity increases. Conversely, machine learning approaches, while powerful, face challenges in interpretability and in handling physical…

Machine Learning · Computer Science 2024-01-31 Jessica Leoni , Valentina Breschi , Simone Formentin , Mara Tanelli

A matching in a two-sided market often incurs an externality: a matched resource may become unavailable to the other side of the market, at least for a while. This is especially an issue in online platforms involving human experts as the…

Artificial Intelligence · Computer Science 2018-10-30 Virag Shah , Lennart Gulikers , Laurent Massoulie , Milan Vojnovic

Deep learning yields great results across many fields, from speech recognition, image classification, to translation. But for each problem, getting a deep model to work well involves research into the architecture and a long period of…

Machine Learning · Computer Science 2017-06-19 Lukasz Kaiser , Aidan N. Gomez , Noam Shazeer , Ashish Vaswani , Niki Parmar , Llion Jones , Jakob Uszkoreit

Neural network based models have achieved impressive results on various specific tasks. However, in previous works, most models are learned separately based on single-task supervised objectives, which often suffer from insufficient training…

Computation and Language · Computer Science 2016-09-26 Pengfei Liu , Xipeng Qiu , Xuanjing Huang

In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the need for heavy computation as required in traditional…

Low-Rank Adaptation (LoRA) is a popular technique for parameter-efficient fine-tuning of Large Language Models (LLMs). We study how different LoRA modules can be merged to achieve skill composition -- testing the performance of the merged…

Computation and Language · Computer Science 2024-12-03 Akshara Prabhakar , Yuanzhi Li , Karthik Narasimhan , Sham Kakade , Eran Malach , Samy Jelassi

The Mixture-of-Experts (MoE) architecture enables a significant increase in the total number of model parameters with minimal computational overhead. However, it is not clear what performance tradeoffs, if any, exist between MoEs and…

The Mixture of Experts (MoE) for language models has been proven effective in augmenting the capacity of models by dynamically routing each input token to a specific subset of experts for processing. Despite the success, most existing…

Machine Learning · Computer Science 2024-07-26 Hao Zhao , Zihan Qiu , Huijia Wu , Zili Wang , Zhaofeng He , Jie Fu