English
Related papers

Related papers: The Non-Local Model Merging Problem: Permutation S…

200 papers

Recent advances in large language models have led to numerous task-specialized fine-tuned variants, creating a need for efficient model merging techniques that preserve specialized capabilities while avoiding costly retraining. While…

Computation and Language · Computer Science 2025-02-20 Shuqi Liu , Han Wu , Bowei He , Xiongwei Han , Mingxuan Yuan , Linqi Song

Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging in the context of large (~100B) models, by recycling…

Computation and Language · Computer Science 2025-02-05 Muhammad Khalifa , Yi-Chern Tan , Arash Ahmadian , Tom Hosking , Honglak Lee , Lu Wang , Ahmet Üstün , Tom Sherborne , Matthias Gallé

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

The Mixture-of-Experts (MoE) technique has proven to be a promising solution to efficiently scale the model size, which has been widely applied in recent LLM advancements. However, the substantial memory overhead of MoE models has made…

Machine Learning · Computer Science 2025-10-17 Ruijie Miao , Yilun Yao , Zihan Wang , Zhiming Wang , Bairen Yi , LingJun Liu , Yikai Zhao , Tong Yang

Model merging aims to integrate multiple task-specific models into a unified model that inherits the capabilities of the task-specific models, without additional training. Existing model merging methods often lack consideration of the…

Computation and Language · Computer Science 2025-08-07 Yue Zhou , Yi Chang , Yuan Wu

To address the performance limitations of the Segment Anything Model (SAM) in specific domains, existing works primarily adopt adapter-based one-step adaptation paradigms. However, some of these methods are specific developed for specific…

Machine Learning · Computer Science 2025-07-17 Yuan-Chen Shu , Zhiwei Lin , Yongtao Wang

Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has…

Computation and Language · Computer Science 2024-10-22 Mingxin Li , Zhijie Nie , Yanzhao Zhang , Dingkun Long , Richong Zhang , Pengjun Xie

Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this line of work has not yet extended to the Transformer…

Computation and Language · Computer Science 2024-12-17 Neha Verma , Maha Elbayad

Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without…

Machine Learning · Computer Science 2026-02-10 Tiantong Wang , Yiyang Duan , Haoyu Chen , Tiantong Wu , Wei Yang Bryan Lim

General-purpose text embedding models underpin a wide range of NLP and information retrieval applications, and are typically trained on large-scale multi-task corpora to encourage broad generalization. However, it remains unclear how…

Information Retrieval · Computer Science 2026-02-10 Hengran Zhang , Keping Bi , Jiafeng Guo , Jiaming Zhang , Wenbo Yang , Daiting Shi , Xueqi Cheng

We study empirical scaling laws for language model merging measured by cross-entropy. Despite its wide practical use, merging lacks a quantitative rule that predicts returns as we add experts or scale the model size. We identify a compact…

Artificial Intelligence · Computer Science 2026-05-12 Yuanyi Wang , Yanggan Gu , Yiming Zhang , Qi Zhou , Zhaoyi Yan , Congkai Xie , Xinyao Wang , Jianbo Yuan , Hongxia Yang

In medical imaging, vision-language models face a critical duality: pretrained networks offer broad robustness but lack subtle, modality-specific characteristics, while fine-tuned expert models achieve high in-distribution accuracy yet…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Raza Imam , Hu Wang , Dwarikanath Mahapatra , Mohammad Yaqub

Recent research advocates deploying smaller, specialized code LLMs in agentic frameworks alongside frontier models, sparking interest in efficient strategies for multi-task learning that balance performance, constraints, and costs. We…

Computation and Language · Computer Science 2026-01-30 Mingzhi Zhu , Boris Sobolev , Rahul Krishna , Raju Pavuluri , Stacy Patterson , Michele Merler

Permutation symmetries of deep networks make basic operations like model merging and similarity estimation challenging. In many cases, aligning the weights of the networks, i.e., finding optimal permutations between their weights, is…

Machine Learning · Computer Science 2024-11-12 Aviv Navon , Aviv Shamsian , Ethan Fetaya , Gal Chechik , Nadav Dym , Haggai Maron

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

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 aims to integrate multiple task-adapted models into a unified model that preserves the knowledge of each task. In this paper, we identify that the key to this knowledge retention lies in maintaining the directional consistency…

Machine Learning · Computer Science 2026-03-17 Han-Chen Zhang , Zi-Hao Zhou , Mao-Lin Luo , Shimin Di , Min-Ling Zhang , Tong Wei

When finetuning multiple tasks altogether, it is important to carefully weigh them to get a good performance, but searching for good weights can be difficult and costly. Here, we propose to aid the search with fast previews to quickly get a…

Machine Learning · Computer Science 2024-12-12 Hugo Monzón Maldonado , Thomas Möllenhoff , Nico Daheim , Iryna Gurevych , Mohammad Emtiyaz Khan

Recent works suggest that transformer models are capable of multi-tasking on diverse NLP tasks and adapting to new tasks efficiently. However, the potential of these multi-task models may be limited as they use the same set of parameters…

Computation and Language · Computer Science 2022-11-23 Qinyuan Ye , Juan Zha , Xiang Ren

Merging parameters of multiple models has resurfaced as an effective strategy to enhance task performance and robustness, but prior work is limited by the high costs of ensemble creation and inference. In this paper, we leverage the…

Computer Vision and Pattern Recognition · Computer Science 2024-09-25 Roberto Alcover-Couso , Juan C. SanMiguel , Marcos Escudero-Viñolo , Jose M Martínez