Related papers: Multi-Level Collaboration in Model Merging

Model merging acquires general capabilities without extra data or training by combining multiple models' parameters. Previous approaches achieve linear mode connectivity by aligning parameters into the same loss basin using permutation…

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…

Model merging combines fine-tuned checkpoints into a single multi-task model without retraining. Existing methods - such as task arithmetic, model soups, TIES, and DARE - are computationally efficient and empirically successful, but rely on…

A critical decision point when training predictors using multiple studies is whether studies should be combined or treated separately. We compare two multi-study prediction approaches in the presence of potential heterogeneity in…

Merging has become a widespread way to cheaply combine individual models into a single model that inherits their capabilities and attains better performance. This popularity has spurred rapid development of many new merging methods, which…

Multi-task learning (MTL) aims to empower a model to tackle multiple tasks simultaneously. A recent development known as task arithmetic has revealed that several models, each fine-tuned for distinct tasks, can be directly merged into a…

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…

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,…

Models trained on different datasets can be merged by a weighted-averaging of their parameters, but why does it work and when can it fail? Here, we connect the inaccuracy of weighted-averaging to mismatches in the gradients and propose a…

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Merging Large Language Models (LLMs) is a cost-effective technique for combining multiple expert LLMs into a single versatile model, retaining the expertise of the original ones. However, current approaches often overlook the importance of…

Multimodal Large Language Models (MLLMs) have achieved success across various domains. However, their applicability tends to degrade when confronted with different types of data inputs, especially for MLLMs that have been fine-tuned for…

Model merging is a flexible and computationally tractable approach to merge single-task checkpoints into a multi-task model. Prior work has solely focused on constrained multi-task settings where there is a one-to-one mapping between a…

Model merging has emerged as a practical paradigm for integrating multiple independently trained models into a single model without joint retraining. Previous studies have demonstrated the effectiveness of combining parameters through…

Recent advances in large language models (LLMs) have been largely driven by scaling laws for individual models, which predict performance improvements as model parameters and data volume increase. However, the capabilities of any single LLM…

The recent success of specialized Large Language Models (LLMs) in domains such as mathematical reasoning and coding has led to growing interest in methods for merging these expert LLMs into a unified Mixture-of-Experts (MoE) model, with the…

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…

Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Existing methods like data mixture strategies face limitations,…

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…

State-of-the-art vision-and-language models consist of many parameters and learn from enormous datasets, surpassing the amounts of linguistic data that children are exposed to as they acquire a language. This paper presents our approach to…