Related papers: EMR-Merging: Tuning-Free High-Performance Model Me…

Deep model training on extensive datasets is increasingly becoming cost-prohibitive, prompting the widespread adoption of deep model fusion techniques to leverage knowledge from pre-existing models. From simple weight averaging to more…

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…

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we…

Task arithmetic is a straightforward yet highly effective strategy for model merging, enabling the resultant model to exhibit multi-task capabilities. Recent research indicates that models demonstrating linearity enhance the performance of…

Selecting the best data mixture is critical for successful Supervised Fine-Tuning (SFT) of Multimodal Large Language Models. However, determining the optimal mixture weights across multiple domain-specific datasets remains a significant…

This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified…

Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, most evaluations of model merging in computer vision are…

Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and…

Parameter-level model merging is an emerging paradigm in multi-task learning with significant promise. Previous research has explored its connections with prediction-level model ensembling-commonly viewed as the upper bound for merging-to…

This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from…

Large pre-trained models have enabled significant advances in machine learning and served as foundation components. Model fusion methods, such as task arithmetic, have been proven to be powerful and scalable to incorporate fine-tuned…

Large Language Models (LLMs) remain heavily centered on English, with limited performance in low-resource languages. Existing adaptation approaches, such as continual pre-training, demand significant computational resources. In the case of…

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…

Large language models (LLMs) still struggle across tasks outside of high-resource languages. In this work, we investigate cross-lingual transfer to lower-resource languages where task-specific post-training data is scarce. Building on prior…

Low-resource deployment constraints have made model quantization essential for deploying neural networks while preserving performance. Meanwhile, model merging has become an increasingly practical low-resource strategy for integrating…

Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetuned models become publicly available, concerns about the…

Automatic Speech Recognition (ASR) has advanced with Speech Foundation Models (SFMs), yet performance degrades on dysarthric speech due to variability and limited data. This study as part of the submission to the Speech Accessibility…

Pretrained models are the standard starting point for training. This approach consistently outperforms the use of a random initialization. However, pretraining is a costly endeavour that few can undertake. In this paper, we create better…

Weight-space model merging combines independently fine-tuned models without accessing original training data, offering a practical alternative to joint training. While merging succeeds in multitask settings, its behavior in multilingual…

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…