Related papers: MagMax: Leveraging Model Merging for Seamless Cont…

Model merging is an effective strategy to merge multiple models for enhancing model performances, and more efficient than ensemble learning as it will not introduce extra computation into inference. However, limited research explores if the…

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Continual learning aims to learn knowledge of tasks observed in sequential time steps while mitigating the forgetting of previously learned knowledge. Existing methods were designed to learn a single modality (e.g., image) over time, which…

Multi-task learning (MTL) is often achieved by merging datasets before fine-tuning, but the growing availability of fine-tuned models has led to new approaches such as model merging via task arithmetic. A major challenge in this setting is…

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching…

The success of pretrain-finetune paradigm brings about the release of numerous model weights. In this case, merging models finetuned on different tasks to enable a single model with multi-task capabilities is gaining increasing attention…

Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of…

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Model merging has gained prominence in machine learning as a method to integrate multiple trained models into a single model without accessing the original training data. While existing approaches have demonstrated success in domains such…

Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities from other specialized LLMs. Popular methods like ensemble…

In recent years, model-agnostic meta-learning (MAML) has become a popular research area. However, the stochastic optimization of MAML is still underdeveloped. Existing MAML algorithms rely on the ``episode'' idea by sampling a few tasks and…

Recent advancements in building domain-specific large language models (LLMs) have shown remarkable success, especially in tasks requiring reasoning abilities like logical inference over complex relationships and multi-step problem solving.…

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…

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Model merging offers a training-free alternative to multi-task learning by combining independently fine-tuned models into a unified one without access to raw data. However, existing approaches often rely on heuristics to determine the…

Recent research efforts in lifelong learning propose to grow a mixture of models to adapt to an increasing number of tasks. The proposed methodology shows promising results in overcoming catastrophic forgetting. However, the theory behind…

Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key…

Given access to accurate dynamical models, modern planning approaches are effective in computing feasible and optimal plans for repetitive robotic tasks. However, it is difficult to model the true dynamics of the real world before…

Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. Considering the heavy cost of training MLLMs, it is efficient to reuse the existing ones and…

Choosing a suitable deep learning architecture for multimodal data fusion is a challenging task, as it requires the effective integration and processing of diverse data types, each with distinct structures and characteristics. In this…