Related papers: Tunable MAGMAX: Preference-Aware Model Merging for…

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

While most current approaches rely on further training techniques, such as fine-tuning or reinforcement learning, to enhance model capacities, model merging stands out for its ability of improving models without requiring any additional…

Model merging aims to build a multi-task learner by combining the parameters of individually fine-tuned models without additional training. While a straightforward approach is to average model parameters across tasks, this often results in…

Multi-Task Learning (MTL) involves the concurrent training of multiple tasks, offering notable advantages for dense prediction tasks in computer vision. MTL not only reduces training and inference time as opposed to having multiple…

Continual learning (CL) is a major challenge of machine learning (ML) and describes the ability to learn several tasks sequentially without catastrophic forgetting (CF). Recent works indicate that CL is a complex topic, even more so when…

The size and the computational load of fine-tuning large-scale pre-trained neural network are becoming two major obstacles in adopting machine learning in many applications. Continual learning (CL) can serve as a remedy through enabling…

Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computational resources and labeled data, lacking a paradigm that can…

Motivated by the efficiency and rapid convergence of pre-trained models for solving downstream tasks, this paper extensively studies the impact of Continual Learning (CL) models as pre-trainers. In both supervised and unsupervised CL, we…

By exploiting the correlation between the structure and the solution of Mixed-Integer Linear Programming (MILP), Machine Learning (ML) has become a promising method for solving large-scale MILP problems. Existing ML-based MILP solvers…

Continual learning (CL) aims to train deep neural networks efficiently on streaming data while limiting the forgetting caused by new tasks. However, learning transferable knowledge with less interference between tasks is difficult, and…

Recently, continual learning (CL) has gained significant interest because it enables deep learning models to acquire new knowledge without forgetting previously learnt information. However, most existing works require knowing the task…

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data…

When faced with learning a set of inter-related tasks from a limited amount of usable data, learning each task independently may lead to poor generalization performance. Multi-Task Learning (MTL) exploits the latent relations between tasks…

The "pre-training $\rightarrow$ downstream adaptation" presents both new opportunities and challenges for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through Parameter-Efficient-Tuning (PET) adaptation…

Class-Incremental Learning (CIL) aims to learn new classes sequentially while retaining the knowledge of previously learned classes. Recently, pre-trained models (PTMs) combined with parameter-efficient fine-tuning (PEFT) have shown…

Recent advances in large language models have led to specialized models excelling in specific domains, creating a need for efficient model merging techniques. While traditional merging approaches combine parameters into a single static…

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…

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…

Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning…

Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integration of diverse LLMs, the overall competency of LLMs is…