English
Related papers

Related papers: Mashup Learning: Faster Finetuning by Remixing Pas…

200 papers

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Machine Learning · Computer Science 2025-10-21 Yifei He , Siqi Zeng , Yuzheng Hu , Rui Yang , Tong Zhang , Han Zhao

Fine-tuning large language models (LLMs) is intended to improve their reasoning capabilities, yet we uncover a counterintuitive effect: models often forget how to solve problems they previously answered correctly during training. We term…

Artificial Intelligence · Computer Science 2025-05-27 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Bhaskar Ramasubramanian , Luyao Niu , Bill Yuchen Lin , Xiang Yue , Radha Poovendran

Domain reweighting can improve sample efficiency and downstream generalization, but data-mixture optimization for multimodal midtraining remains largely unexplored. Current multimodal training recipes tune mixtures along a single dimension,…

Machine Learning · Computer Science 2026-04-17 Bingbing Wen , Sirajul Salekin , Feiyang Kang , Bill Howe , Lucy Lu Wang , Javier Movellan , Manjot Bilkhu

Data selection for finetuning Large Language Models (LLMs) can be framed as a budget-constrained optimization problem: maximizing a model's downstream performance under a strict training data budget. Solving this problem is generally…

Machine Learning · Computer Science 2025-10-01 Animesh Jha , Harshit Gupta , Ananjan Nandi

MixUp is a computer vision data augmentation technique that uses convex interpolations of input data and their labels to enhance model generalization during training. However, the application of MixUp to the natural language understanding…

Computation and Language · Computer Science 2021-02-24 Wancong Zhang , Ieshan Vaidya

In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption,…

Machine Learning · Computer Science 2020-01-24 Cheolhyoung Lee , Kyunghyun Cho , Wanmo Kang

Machine learning techniques are used in a wide range of domains. However, machine learning models often suffer from the problem of over-fitting. Many data augmentation methods have been proposed to tackle such a problem, and one of them is…

Machine Learning · Statistics 2021-06-21 Masanari Kimura

Neural networks offer high-accuracy solutions to a range of problems, but are costly to run in production systems because of computational and memory requirements during a forward pass. Given a trained network, we propose a techique called…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Michele Pratusevich

Instruction tuning is crucial for aligning Large Language Models (LLMs), yet the quality of instruction-following data varies significantly. While high-quality data is paramount, it is often scarce; conversely, abundant low-quality data is…

Computation and Language · Computer Science 2025-10-24 Zhijie Deng , Zhouan Shen , Ling Li , Yao Zhou , Zhaowei Zhu , Yanji He , Wei Wang , Jiaheng Wei

Large Language Models (LLMs) have the unique capability to understand and generate human-like text from input queries. When fine-tuned, these models show enhanced performance on domain-specific queries. OpenAI highlights the process of…

Computation and Language · Computer Science 2024-07-02 Scott Barnett , Zac Brannelly , Stefanus Kurniawan , Sheng Wong

Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks. Previous work has shown that scaling the number of training…

Computation and Language · Computer Science 2023-02-10 Joel Jang , Seungone Kim , Seonghyeon Ye , Doyoung Kim , Lajanugen Logeswaran , Moontae Lee , Kyungjae Lee , Minjoon Seo

Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and then performs uniform data sampling across each domain.…

Computation and Language · Computer Science 2025-03-04 Xiangyu Xi , Deyang Kong , Jian Yang , Jiawei Yang , Zhengyu Chen , Wei Wang , Jingang Wang , Xunliang Cai , Shikun Zhang , Wei Ye

Mixup is a data augmentation technique that relies on training using random convex combinations of data points and their labels. In recent years, Mixup has become a standard primitive used in the training of state-of-the-art image…

Machine Learning · Computer Science 2024-11-06 Muthu Chidambaram , Xiang Wang , Chenwei Wu , Rong Ge

Large Language Models are traditionally finetuned on large instruction datasets. However recent studies suggest that small, high-quality datasets can suffice for general purpose instruction following. This lack of consensus surrounding…

Machine Learning · Computer Science 2023-12-29 Aditi Jha , Sam Havens , Jeremy Dohmann , Alex Trott , Jacob Portes

We investigate the use of in-context learning and prompt engineering to estimate the contributions of training data in the outputs of instruction-tuned large language models (LLMs). We propose two novel approaches: (1) a similarity-based…

Computation and Language · Computer Science 2025-03-20 Milad Fotouhi , Mohammad Taha Bahadori , Oluwaseyi Feyisetan , Payman Arabshahi , David Heckerman

Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…

Computation and Language · Computer Science 2025-03-06 Boris Nazarov , Darya Frolova , Yackov Lubarsky , Alexei Gaissinski , Pavel Kisilev

Fine-tuning pre-trained models with custom data leads to numerous expert models on specific tasks. Merging models into one universal model to empower multi-task ability refraining from data leakage has gained popularity. With the expansion…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Fanhu Zeng , Haiyang Guo , Fei Zhu , Li Shen , Hao Tang

How can we teach large multimodal models (LMMs) new skills without erasing prior abilities? We study sequential fine-tuning on five target skills while monitoring general ability on eight held-out benchmarks across three model families.…

Artificial Intelligence · Computer Science 2026-04-22 Zhen Zhu , Yiming Gong , Yao Xiao , Yaoyao Liu , Derek Hoiem

Training Large Language Models (LLMs) incurs significant cost; hence, any strategy that accelerates model convergence is helpful. In this paper, we investigate the ability of a simple idea checkpoint averaging along the trajectory of a…

Machine Learning · Computer Science 2023-12-13 Sunny Sanyal , Atula Neerkaje , Jean Kaddour , Abhishek Kumar , Sujay Sanghavi

Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs), particularly to enhance their reasoning capabilities. However, RL fine-tuning remains highly resource-intensive, and existing work…

Machine Learning · Computer Science 2026-02-17 Yifan Sun , Jingyan Shen , Yibin Wang , Tianyu Chen , Zhendong Wang , Mingyuan Zhou , Huan Zhang