相关论文: Beyond Retention: Orchestrating Structural Safety …

Learning a set of tasks over time, also known as continual learning (CL), is one of the most challenging problems in artificial intelligence due to catastrophic forgetting. Large language models (LLMs) are often impractical to frequent…

Continual learning is a promising machine learning paradigm to learn new tasks while retaining previously learned knowledge over streaming training data. Till now, rehearsal-based methods, keeping a small part of data from old tasks as a…

Online Continual Learning (OCL) is a critical area in machine learning, focusing on enabling models to adapt to evolving data streams in real-time while addressing challenges such as catastrophic forgetting and the stability-plasticity…

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…

Continual learning (CL) has traditionally focused on minimizing exemplar memory, a constraint often misaligned with modern systems where GPU time, not storage, is the primary bottleneck. This paper challenges this paradigm by investigating…

Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation…

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a…

A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new ones. While forgetting has been extensively studied empirically, rigorous theoretical…

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…

Continual learning has become essential in many practical applications such as online news summaries and product classification. The primary challenge is known as catastrophic forgetting, a phenomenon where a model inadvertently discards…

Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is catastrophic forgetting, a phenomenon in which a model…

End-to-end training of Spoken Language Models (SLMs) commonly involves adapting pre-trained text-based Large Language Models (LLMs) to the speech modality through multi-stage training on diverse tasks such as ASR, TTS and spoken question…

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…

Unlearning in large language models (LLMs) has emerged as a promising safeguard against adversarial behaviors. When the forgetting loss is applied uniformly without considering token-level semantic importance, model utility can be…

Catastrophic forgetting affects the training of neural networks, limiting their ability to learn multiple tasks sequentially. From the perspective of the well established plasticity-stability dilemma, neural networks tend to be overly…

Memory-augmented LLM agents offer an appealing shortcut to continual learning: rather than updating model parameters, they accumulate experience in external memory, seemingly sidestepping the stability-plasticity dilemma of parametric…

While large language models have demonstrated impressive performance across various domains and tasks, their security issues have become increasingly severe. Machine unlearning has emerged as a representative approach for model safety and…

Large language models (LLMs) risk retaining unauthorized or sensitive information from their training data, which raises privacy concerns. LLM unlearning seeks to mitigate these risks by selectively removing specified data while maintaining…

Large Language Models (LLMs) exhibit strong general language capabilities. However, fine-tuning these models on domain-specific tasks often leads to catastrophic forgetting, where the model overwrites or loses essential knowledge acquired…

Continual learning algorithms strive to acquire new knowledge while preserving prior information. Often, these algorithms emphasise stability and restrict network updates upon learning new tasks. In many cases, such restrictions come at a…