English
Related papers

Related papers: Orthogonal Model Merging

200 papers

Merging Large Language Models (LLMs) aims to amalgamate multiple homologous LLMs into one with all the capabilities. Ideally, any LLMs sharing the same backbone should be mergeable, irrespective of whether they are Fine-Tuned (FT) with…

Computation and Language · Computer Science 2024-08-07 Le Yu , Bowen Yu , Haiyang Yu , Fei Huang , Yongbin Li

Model merging aims to efficiently combine the weights of multiple expert models, each trained on a specific task, into a single multi-task model, with strong performance across all tasks. When applied to all but the last layer of weights,…

Machine Learning · Computer Science 2024-10-17 Ekansh Sharma , Daniel M. Roy , Gintare Karolina Dziugaite

Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computational resources and labeled data, lacking a paradigm that can…

Computation and Language · Computer Science 2025-03-10 Yiguan Lin , Bin Xu , Yinghao Li , Yang Gao

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

Model merging offers a promising avenue for knowledge integration and parallel development without retraining. Yet, existing methods either ignore the geometry of the loss landscape or rely on intractable full-space Hessian approximations.…

Machine Learning · Computer Science 2026-05-27 Juanwu Lu , Anand Bhaskar , Brian Axelrod , Ekaterina Tolstaya , Tristan Emrich

In this paper, we address the challenges associated with merging low-rank adaptations of large neural networks. With the rise of parameter-efficient adaptation techniques, such as Low-Rank Adaptation (LoRA), model fine-tuning has become…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Aniello Panariello , Daniel Marczak , Simone Magistri , Angelo Porrello , Bartłomiej Twardowski , Andrew D. Bagdanov , Simone Calderara , Joost van de Weijer

Supervised fine-tuning (SFT) is crucial for adapting Large Language Models (LLMs) to specific tasks. In this work, we demonstrate that the order of training data can lead to significant training imbalances, potentially resulting in…

Computation and Language · Computer Science 2024-10-08 Yiming Ju , Ziyi Ni , Xingrun Xing , Zhixiong Zeng , hanyu Zhao , Siqi Fan , Zheng Zhang

Large language models have been adopted in the medical domain for clinical documentation to reduce clinician burden. However, studies have reported that LLMs often "forget" a significant amount of instruction-following ability when…

Computation and Language · Computer Science 2026-04-03 Mengxian Lyu , Cheng Peng , Ziyi Chen , Mengyuan Zhang , Jieting Li Lu , Yonghui Wu

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Machine Learning · Computer Science 2025-10-28 Wenju Sun , Qingyong Li , Wen Wang , Yang Liu , Yangli-ao Geng , Boyang Li

Extensive fine-tuning on Large Language Models does not always yield better results. Oftentimes, models tend to get better at imitating one form of data without gaining greater reasoning ability and may even end up losing some intelligence.…

Neural and Evolutionary Computing · Computer Science 2024-02-02 Yushu Jiang

As the computational demands for pre-training Large Language Models (LLMs) continue to surge, the need for efficient training paradigms becomes critical. Despite the vast resources already invested in existing pre-trained checkpoints, these…

Machine Learning · Computer Science 2026-05-18 Ruizhe Wang , Yucheng Ding , Xiao Liu , Yaoxiang Wang , Peng Cheng , Baining Guo , Zhengjun Zha , Yeyun Gong

Orthogonality constraints naturally appear in many machine learning problems, from principal component analysis to robust neural network training. They are usually solved using Riemannian optimization algorithms, which minimize the…

Machine Learning · Statistics 2025-08-08 Pierre Ablin , Simon Vary , Bin Gao , P. -A. Absil

Orthogonal finetuning (OFT) offers highly parameter-efficient adaptation while preventing catastrophic forgetting, but its high runtime and memory demands limit practical deployment. We identify the core computational bottleneck in OFT as…

Machine Learning · Computer Science 2025-10-16 Zeju Qiu , Weiyang Liu , Adrian Weller , Bernhard Schölkopf

Driven by the rapid growth of model parameters, parameter-efficient fine-tuning (PEFT) has become essential for adapting large models to diverse downstream tasks under constrained computational resources. Within this paradigm, orthogonal…

Machine Learning · Computer Science 2026-02-20 Fei Wu , Jia Hu , Geyong Min , Shiqiang Wang

The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the parameter space. However, two challenges remain: (1) uniform…

Artificial Intelligence · Computer Science 2025-03-28 Jiaqi Han , Jingwen Ye , Shunyu Liu , Haofei Zhang , Jie Song , Zunlei Feng , Mingli Song

Large language models (LLMs) suffer from catastrophic forgetting in sequential multi-task learning. Existing parameter regularization methods (e.g., O-LoRA, N-LoRA) mitigate interference via low-rank subspace orthogonality, but additive…

Computation and Language · Computer Science 2026-01-26 Kefan Cao , Shuaicheng Wu

We propose a new finetuning method to provide pre-trained large language models (LMs) the ability to scale test-time compute through the diffusion framework. By increasing the number of diffusion steps, we show our finetuned models achieve…

Computation and Language · Computer Science 2025-06-04 Edoardo Cetin , Tianyu Zhao , Yujin Tang

Large language model (LLM) alignment faces a critical dilemma when addressing multiple human preferences: improvements in one dimension frequently come at the expense of others, creating unavoidable trade-offs between competing objectives…

Model merging is an effective post-training strategy for composing capabilities in large language models without joint retraining. We study this in the supervised fine-tuning (SFT) stage, where multiple capability-based SFT checkpoints --…

Machine Learning · Computer Science 2025-09-16 Pouria Mahdavinia , Hamed Mahdavi , Niloofar Mireshghallah , Mehrdad Mahdavi

Complex tables with multi-level headers, merged cells and heterogeneous layouts pose persistent challenges for LLMs in both understanding and reasoning. Existing approaches typically rely on table linearization or normalized grid modeling.…

Computation and Language · Computer Science 2026-02-03 Bin Cao , Huixian Lu , Chenwen Ma , Ting Wang , Ruizhe Li , Jing Fan