Related papers: Multi-Level Collaboration in Model Merging

Model merging allows combining the capabilities of existing models into a new one - post hoc, without additional training. This has made it increasingly popular thanks to its low cost and the availability of libraries that support merging…

The rapid proliferation of pretrained models and open repositories has made model merging a convenient yet risky practice, allowing free-riders to combine fine-tuned models into a new multi-capability model without authorization. Such…

Continual learning (CL) aims to train models sequentially on multiple tasks while mitigating catastrophic forgetting of previously learned knowledge. Recent advances in large pre-trained models (LPMs) and model merging techniques, such as…

There is a long history in machine learning of model ensembling, beginning with boosting and bagging and continuing to the present day. Much of this history has focused on combining models for classification and regression, but recently…

Deep neural networks have shown remarkable performance when trained on independent and identically distributed data from a fixed set of classes. However, in real-world scenarios, it can be desirable to train models on a continuous stream of…

The workflow of pretraining and fine-tuning has emerged as a popular paradigm for solving various NLP and V&L (Vision-and-Language) downstream tasks. With the capacity of pretrained models growing rapidly, how to perform parameter-efficient…

We re-evaluate the standard practice of sharing weights between input and output embeddings in state-of-the-art pre-trained language models. We show that decoupled embeddings provide increased modeling flexibility, allowing us to…

Integrating knowledge across different domains is an essential feature of human learning. Learning paradigms such as transfer learning, meta-learning, and multi-task learning reflect the human learning process by exploiting the prior…

There is a growing interest in training domain-expert LLMs that excel in specific technical fields compared to their general-purpose instruction-tuned counterparts. However, these expert models often experience a loss in their safety…

Recent Vision-Language-Action (VLA) models reformulate vision-language models by tuning them with millions of robotic demonstrations. While they perform well when fine-tuned for a single embodiment or task family, extending them to…

Today's generative models are capable of synthesizing high-fidelity images, but each model specializes on a specific target domain. This raises the need for model merging: combining two or more pretrained generative models into a single…

Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these claims by introducing Mirage, a representation-level…

Typical deep visual recognition models are capable of performing the one task they were trained on. In this paper, we tackle the extremely difficult problem of combining distinct models with different initializations, each solving a…

Growing amounts of online user data motivate the need for automated processing techniques. In case of user ratings, one interesting option is to use neural networks for learning to predict ratings given an item and a user. While training…

Multi-task learning (MTL) concurrently trains a model on diverse task datasets to exploit common features, thereby improving overall performance across the tasks. Recent studies have dedicated efforts to merging multiple independent model…

Fine-tuning pretrained models has become a standard pathway to achieve state-of-the-art performance across a wide range of domains, leading to a proliferation of task-specific model variants. As the number of such specialized models…

Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest…

Multitask learning (MTL) aims to learn multiple tasks simultaneously through the interdependence between different tasks. The way to measure the relatedness between tasks is always a popular issue. There are mainly two ways to measure…

Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…

Large language model (LLM) merging has become a key technique in modern LLM development pipelines, enabling the integration of multiple task- or domain-specific expert models without retraining. However, as the number of experts grows,…