相关论文: Multimodal Continual Instruction Tuning with Dynam…

In the present era of deep learning, continual learning research is mainly focused on mitigating forgetting when training a neural network with stochastic gradient descent on a non-stationary stream of data. On the other hand, in the more…

Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic…

Recently, continual graph learning has been increasingly adopted for diverse graph-structured data processing tasks in non-stationary environments. Despite its promising learning capability, current studies on continual graph learning…

Neural machine translation (NMT) models usually suffer from catastrophic forgetting during continual training where the models tend to gradually forget previously learned knowledge and swing to fit the newly added data which may have a…

Multimodal learning typically relies on the assumption that all modalities are fully available during both the training and inference phases. However, in real-world scenarios, consistently acquiring complete multimodal data presents…

Deep learning has proved to be a successful paradigm for solving many challenges in machine learning. However, deep neural networks fail when trained sequentially on multiple tasks, a shortcoming known as catastrophic forgetting in the…

Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…

Overparameterization is known to permit strong generalization performance in neural networks. In this work, we provide an initial theoretical analysis of its effect on catastrophic forgetting in a continual learning setup. We show…

Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade…

To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…

In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important…

Continual learning, the ability of a model to adapt to an ongoing sequence of tasks without forgetting earlier ones, is a central goal of artificial intelligence. To better understand its underlying mechanisms, we study the limitations of…

Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitation of the static…

Large language models often lose previously aligned safety behaviors when fine-tuned on benign data, a phenomenon known as catastrophic forgetting. Prior work shows that adding random safety examples can mitigate this effect, but it remains…

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

Modelling a language model for a multi-lingual scenario includes several potential challenges, among which catastrophic forgetting is the major challenge. For example, small language models (SLM) built for low-resource languages by adapting…

Instruction-tuned large language models (LLMs) have demonstrated promising zero-shot generalization capabilities across various downstream tasks. Recent research has introduced multimodal capabilities to LLMs by integrating independently…

The magnitude of parameter updates are considered a key factor in continual learning. However, most existing studies focus on designing diverse update strategies, while a theoretical understanding of the underlying mechanisms remains…

Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT)…