English
Related papers

Related papers: Model Merging by Output-Space Projection

200 papers

Although multi-task learning is widely applied in intelligent services, traditional multi-task modeling methods often require customized designs based on specific task combinations, resulting in a cumbersome modeling process. Inspired by…

Machine Learning · Computer Science 2025-04-15 Jingxuan Zhou , Weidong Bao , Ji Wang , Zhengyi Zhong , Dayu Zhang

User information needs are often highly diverse and varied. A key challenge in current research is how to achieve controllable multi-objective generation while enabling rapid adaptation to accommodate diverse user demands during test time.…

Machine Learning · Computer Science 2025-06-03 Guofu Xie , Xiao Zhang , Ting Yao , Yunsheng Shi

Model merging has emerged as a compelling data-free paradigm for multi-task learning, enabling the fusion of multiple fine-tuned models into a single, powerful entity. A key technique in merging methods is sparsification, which prunes…

Computation and Language · Computer Science 2025-08-11 Yingfeng Luo , Dingyang Lin , Junxin Wang , Ziqiang Xu , Kaiyan Chang , Tong Zheng , Bei Li , Anxiang Ma , Tong Xiao , Zhengtao Yu , Jingbo Zhu

Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…

Machine Learning · Computer Science 2026-03-12 Sofia Maria Lo Cicero Vaina , Artem Chumachenko , Max Ryabinin

Data-driven approaches such as deep learning can result in predictive models for material properties with exceptional accuracy and efficiency. However, in many applications, data is sparse, severely limiting their accuracy and…

Machine Learning · Computer Science 2025-10-29 Robert J Appleton , Brian C Barnes , Alejandro Strachan

Model merging has emerged as a promising paradigm for enabling multi-task capabilities without additional training. However, existing methods often experience substantial performance degradation compared with individually fine-tuned models,…

Machine Learning · Computer Science 2025-12-02 Kuangpu Guo , Yuhe Ding , Jian Liang , Zilei Wang , Ran He

With the rise and ubiquity of larger deep learning models, the need for high-quality compression techniques is growing in order to deploy these models widely. The sheer parameter count of these models makes it difficult to fit them into the…

Computation and Language · Computer Science 2025-04-01 Neha Verma , Kenton Murray , Kevin Duh

We present a holistic framework for Continual Model Merging (CMM) that intervenes at three critical stages: pre-merging, during merging, and post-merging-to address two fundamental challenges in continual learning. In particular,…

Machine Learning · Computer Science 2026-02-23 Hoang Phan , Sungmin Cha , Tung Lam Tran , Qi Lei

With the development of large language models, fine-tuning has emerged as an effective method to enhance performance in specific scenarios by injecting domain-specific knowledge. In this context, model merging techniques provide a solution…

Computation and Language · Computer Science 2025-09-18 Zijian Li , Xiaocheng Feng , Huixin Liu , Yichong Huang , Ting Liu , Bing Qin

As scaled language models (LMs) approach human-level reasoning capabilities, self-improvement emerges as a solution to synthesizing high-quality data corpus. While previous research has identified model collapse as a risk in…

Computation and Language · Computer Science 2025-10-28 Xiangchi Yuan , Chunhui Zhang , Zheyuan Liu , Dachuan Shi , Leyan Pan , Soroush Vosoughi , Wenke Lee

Model merging aggregates Large Language Models (LLMs) finetuned on different tasks into a stronger one. However, parameter conflicts between models leads to performance degradation in averaging. While model routing addresses this issue by…

Machine Learning · Computer Science 2025-02-12 Kunfeng Lai , Zhenheng Tang , Xinglin Pan , Peijie Dong , Xiang Liu , Haolan Chen , Li Shen , Bo Li , Xiaowen Chu

Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integration of diverse LLMs, the overall competency of LLMs is…

Computation and Language · Computer Science 2024-12-23 Mingyang Zhang , Jing Liu , Ganggui Ding , Xinyi Yu , Linlin Ou , Bohan Zhuang

We study model merging as a practical alternative to conventional adaptation strategies for code-mixed NLP. Starting from a multilingual base model, we: (i) perform continued pre-training (CPT) on unlabeled code-mixed text to obtain an…

Computation and Language · Computer Science 2025-10-24 Prashant Kodali , Vaishnavi Shivkumar , Swarang Joshi , Monojit Choudhary , Ponnurangam Kumaraguru , Manish Shrivastava

Modeling complex physical systems such as they arise in civil engineering applications requires finding a trade-off between physical fidelity and practicality. Consequently, deviations of simulation from measurements are ubiquitous even…

Computational Engineering, Finance, and Science · Computer Science 2026-03-18 Paolo Villani , Daniel Andrés Arcones , Jörg F. Unger , Martin Weiser

In real-world machine learning deployments, models must be continually updated, composed, and when required, selectively undone. However, existing approaches to model merging and continual learning often suffer from task interference,…

Machine Learning · Computer Science 2026-04-14 Haris Khan , Sadia Asif , Shumaila Asif , Muhammad Zeeshan Karamat , Rajesh Upadhayaya

The matching of multiple objects (e.g. shapes or images) is a fundamental problem in vision and graphics. In order to robustly handle ambiguities, noise and repetitive patterns in challenging real-world settings, it is essential to take…

Computer Vision and Pattern Recognition · Computer Science 2019-03-15 Florian Bernard , Johan Thunberg , Paul Swoboda , Christian Theobalt

Many robotics applications require alignment and fusion of observations obtained at multiple views to form a global model of the environment. Multi-way data association methods provide a mechanism to improve alignment accuracy of pairwise…

Robotics · Computer Science 2020-03-06 Kaveh Fathian , Kasra Khosoussi , Yulun Tian , Parker Lusk , Jonathan P. How

Model merging has emerged as a lightweight paradigm for enhancing Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. In this work, we analyze late-stage pre-training trajectories and uncover a…

Machine Learning · Computer Science 2026-05-27 Wenjie Zhou , Bohan Wang , Hongtao Zhang , Chenxi Jia , Wei Chen , Xueqi Cheng

Improvement of time series forecasting accuracy through combining multiple models is an important as well as a dynamic area of research. As a result, various forecasts combination methods have been developed in literature. However, most of…

Artificial Intelligence · Computer Science 2013-02-28 Ratnadip Adhikari , R. K. Agrawal

Recent research has increasingly focused on reconciling the reasoning capabilities of System 2 with the efficiency of System 1. While existing training-based and prompt-based approaches face significant challenges in terms of efficiency and…

Computation and Language · Computer Science 2025-11-17 Yuxuan Yao , Shuqi Liu , Zehua Liu , Qintong Li , Mingyang Liu , Xiongwei Han , Zhijiang Guo , Han Wu , Linqi Song
‹ Prev 1 8 9 10 Next ›