English
Related papers

Related papers: Orthogonal Model Merging

200 papers

Expanding Large Language Models~(LLMs) to new languages is a costly endeavor, demanding extensive Continued Pre-Training~(CPT) and data-intensive alignment. While recent data-free merging techniques attempt to bypass alignment by fusing a…

Computation and Language · Computer Science 2026-05-19 Hao Zhou , Tianhao Li , Zhijun Wang , Shuaijie She , Linjuan Wu , Hao-Ran Wei , Baosong Yang , Jiajun Chen , Shujian Huang

Precise spatial modeling in the operating room (OR) is foundational to many clinical tasks, supporting intraoperative awareness, hazard avoidance, and surgical decision-making. While existing approaches leverage large-scale multimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Peiqi He , Zhenhao Zhang , Yixiang Zhang , Xiongjun Zhao , Shaoliang Peng

Regression Mean (RegMean), an approach that formulates model merging as a linear regression problem, aims to find the optimal weights for each linear layer in the merged model by minimizing the discrepancy in predictions between the merged…

Machine Learning · Computer Science 2026-04-28 The-Hai Nguyen , Dang Huu-Tien , Takeshi Suzuki , Le-Minh Nguyen

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Ibrahim Almakky , Santosh Sanjeev , Anees Ur Rehman Hashmi , Mohammad Areeb Qazi , Hu Wang , Mohammad Yaqub

Lithography is fundamental to integrated circuit fabrication, necessitating large computation overhead. The advancement of machine learning (ML)-based lithography models alleviates the trade-offs between manufacturing process expense and…

Computer Vision and Pattern Recognition · Computer Science 2023-04-11 Guojin Chen , Zehua Pei , Haoyu Yang , Yuzhe Ma , Bei Yu , Martin D. F. Wong

Recent advances in Vision-Language Models (VLMs) have motivated the development of multi-modal search agents that can actively invoke external search tools and integrate retrieved evidence through multi-step reasoning. While promising,…

Artificial Intelligence · Computer Science 2026-03-03 Zhixiang Wang , Jingxuan Xu , Dajun Chen , Yunfang Wu , Wei Jiang , Yong Li

The pre-trained language models are continually fine-tuned to better support downstream applications. However, this operation may result in significant performance degeneration on general tasks beyond the targeted domain. To overcome this…

Computation and Language · Computer Science 2023-12-11 Shitao Xiao , Zheng Liu , Peitian Zhang , Xingrun Xing

While large pre-trained models have achieved impressive performance across AI tasks, their deployment in privacy-sensitive and distributed environments remains challenging. Federated learning (FL) offers a viable solution by enabling…

Machine Learning · Computer Science 2025-08-26 Ruofan Jia , Weiying Xie , Jie Lei , Jitao Ma , Haonan Qin , Leyuan Fang

We propose an overlapping Schwarz space-time refinement framework for the material point method (OS-MPM) to improve computational efficiency in problems with strongly localized deformation, contact, and large geometric nonlinearity. The…

Computational Engineering, Finance, and Science · Computer Science 2026-05-12 Zhaofeng Luo , Minchen Li , Yupeng Jiang

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less…

Computation and Language · Computer Science 2024-10-25 Zouying Cao , Yifei Yang , Hai Zhao

Fine-tuning pre-trained models for downstream tasks is a widely adopted technique known for its adaptability and reliability across various domains. Despite its conceptual simplicity, fine-tuning entails several troublesome engineering…

Artificial Intelligence · Computer Science 2024-12-30 Chaeyun Jang , Hyungi Lee , Jungtaek Kim , Juho Lee

Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a small subset of parameters. However, both approaches have…

Artificial Intelligence · Computer Science 2026-04-14 Shaocong Ma , Peiran Yu , Heng Huang

Orthopoxvirus infections must be accurately classified from medical pictures for an easy and early diagnosis and epidemic prevention. The necessity for automated and scalable solutions is highlighted by the fact that traditional diagnostic…

Computer Vision and Pattern Recognition · Computer Science 2025-06-09 Alejandro Puente-Castro , Enrique Fernandez-Blanco , Daniel Rivero , Andres Molares-Ulloa

Model merging provides a cost-effective and data-efficient combination of specialized deep neural networks through parameter integration. This technique leverages expert models across downstream tasks without requiring retraining. Most…

Machine Learning · Computer Science 2025-10-17 Levy Chaves , Eduardo Valle , Sandra Avila

The large language model (LLM) is typically integrated into the mainstream optimization protocol. No work has questioned whether maintaining the model integrity is \textit{indispensable} for promising performance. In this work, we introduce…

Computation and Language · Computer Science 2026-03-17 Mingyuan Zhang , Yue Bai , Huan Wang , Yizhou Wang , Qihua Dong , Yitian Zhang , Yun Fu

Machine Unlearning has emerged as a significant area of research, focusing on `removing' specific subsets of data from a trained model. Fine-tuning (FT) methods have become one of the fundamental approaches for approximating unlearning, as…

Machine Learning · Computer Science 2025-11-25 Meng Ding , Rohan Sharma , Changyou Chen , Jinhui Xu , Kaiyi Ji

Multi-Task Learning (MTL) seeks to boost statistical power and learning efficiency by discovering structure shared across related tasks. State-of-the-art MTL representation methods, however, usually treat the latent representation matrix as…

Machine Learning · Statistics 2025-05-07 Aoran Chen , Yang Feng

Machine unlearning aims to selectively remove specific knowledge from a trained model. Existing approaches, such as Task Arithmetic, fine-tune the model on the forget set to create a task vector (i.e., a direction in weight space) for…

Machine Learning · Computer Science 2025-07-03 Hyo Seo Kim , Dongyoon Han , Junsuk Choe

Embedding models trained separately on similar data often produce representations that encode stable information but are not directly interchangeable. This lack of interoperability raises challenges in several practical applications, such…

Machine Learning · Computer Science 2025-10-16 Lucas Maystre , Alvaro Ortega Gonzalez , Charles Park , Rares Dolga , Tudor Berariu , Yu Zhao , Kamil Ciosek

Large language models (LLMs) are pretrained by minimizing the cross-entropy loss for next-token prediction. In this paper, we study whether this optimization strategy can induce geometric structure in the learned model weights and context…

Optimization and Control · Mathematics 2026-05-14 Zhehang Du , Hangfeng He , Weijie Su
‹ Prev 1 8 9 10 Next ›