相关论文: Transforming Vision Transformer: Towards Efficient…

In multi-task learning (MTL), related tasks learn jointly to improve generalization performance. To exploit the high learning speed of extreme learning machines (ELMs), we apply the ELM framework to the MTL problem, where the output weights…

Multi-task learning (MTL) is a subfield of machine learning in which multiple tasks are simultaneously learned by a shared model. Such approaches offer advantages like improved data efficiency, reduced overfitting through shared…

Recent advances in Federated Learning (FL) have paved the way towards the design of novel strategies for solving multiple learning tasks simultaneously, by leveraging cooperation among networked devices. Multi-Task Learning (MTL) exploits…

In this paper, we explore multi-task learning (MTL) as a second pretraining step to learn enhanced universal language representation for transformer language models. We use the MTL enhanced representation across several natural language…

Instruction Tuning has the potential to stimulate or enhance specific capabilities of large language models (LLMs). However, achieving the right balance of data is crucial to prevent catastrophic forgetting and interference between tasks.…

Transformer neural networks are increasingly replacing prior architectures in a wide range of applications in different data modalities. The increasing size and computational demands of fine-tuning large pre-trained transformer neural…

Jointly learning multiple tasks with a unified model can improve accuracy and data efficiency, but it faces the challenge of task interference, where optimizing one task objective may inadvertently compromise the performance of another. A…

Intelligent agents should have the ability to leverage knowledge from previously learned tasks in order to learn new ones quickly and efficiently. Meta-learning approaches have emerged as a popular solution to achieve this. However,…

In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require massive amounts of data for training and induce high resource…

Continual learning in Neural Machine Translation (NMT) faces the dual challenges of catastrophic forgetting and the high computational cost of retraining. This study establishes Low-Rank Adaptation (LoRA) as a parameter-efficient framework…

We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a more…

Low-Rank Adaptation (LoRA) is a widely used parameter-efficient fine-tuning method for foundation models, but it suffers from parameter interference, resulting in suboptimal performance. Although Mixture-of-Experts (MoE)-based LoRA variants…

Parameter-Efficient Fine-Tuning (PEFT) has become a dominant paradigm for deploying LLMs in multi-task scenarios due to its extreme parameter efficiency. While Mixture-of-Experts (MoE) based LoRA variants have achieved promising results by…

Multi-Task Learning (MTL) enables multiple tasks to be learned within a shared network, but differences in objectives across tasks can cause negative transfer, where the learning of one task degrades another task's performance. While…

Multi-task learning (MTL) seeks to learn a single model to accomplish multiple tasks by leveraging shared information among the tasks. Existing MTL models, however, have been known to suffer from negative interference among tasks. Efforts…

Visual deep reinforcement learning (RL) enables robots to acquire skills from visual input for unstructured tasks. However, current algorithms suffer from low sample efficiency, limiting their practical applicability. In this work, we…

Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models (MLLMs) to incrementally learn new tasks over time. However, this process is challenged by catastrophic forgetting, where performance on previously learned…

In response to the challenges posed by the extensive parameter updates required for full fine-tuning of large-scale pre-trained models, parameter-efficient fine-tuning (PEFT) methods, exemplified by Low-Rank Adaptation (LoRA), have emerged.…

Explorations in fine-tuning Vision-Language Models (VLMs), such as Low-Rank Adaptation (LoRA) from Parameter Efficient Fine-Tuning (PEFT), have made impressive progress. However, most approaches rely on explicit weight updates, overlooking…

The scalability of deep learning models is fundamentally limited by computing resources, memory, and communication. Although methods like low-rank adaptation (LoRA) have reduced the cost of model finetuning, its application in model…