Related papers: CurLL: A Developmental Framework to Evaluate Conti…
In this paper, we propose a general framework in continual learning for generative models: Feature-oriented Continual Learning (FoCL). Unlike previous works that aim to solve the catastrophic forgetting problem by introducing regularization…
In-context learning (ICL) enables large language models (LLMs) to perform new tasks by prompting them with a sequence of training examples. However, it is known that ICL is very sensitive to the choice of training examples: randomly…
Continual learning (CL) is concerned with learning multiple tasks sequentially without forgetting previously learned tasks. Despite substantial empirical advances over recent years, the theoretical development of CL remains in its infancy.…
The remarkable ability of Large Language Models (LLMs) to understand and follow instructions has sometimes been limited by their in-context learning (ICL) performance in low-resource languages. To address this, we introduce a novel approach…
Efficiently managing compute resources for Large Language Model (LLM) inference remains challenging due to the inherently stochastic and variable lengths of autoregressive text generation. Accurately estimating response lengths in advance…
Deep neural networks, despite their remarkable success, remain fundamentally limited in their ability to perform Continual Learning (CL). While most current methods aim to enhance the capabilities of a single model, Inspired by the…
Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…
In real-world environments, continual learning is essential for machine learning models, as they need to acquire new knowledge incrementally without forgetting what they have already learned. While pretrained language models have shown…
We examine the language capabilities of language models (LMs) from the critical perspective of human language acquisition. Building on classical language development theories, we propose a three-stage framework to assess the abilities of…
This paper develops variational continual learning (VCL), a simple but general framework for continual learning that fuses online variational inference (VI) and recent advances in Monte Carlo VI for neural networks. The framework can…
Continual instruction tuning(CIT) during the post-training phase is crucial for adapting multimodal large language models (MLLMs) to evolving real-world demands. However, the progress is hampered by the lack of benchmarks with rigorous,…
Pre-trained Large Language Models (LLMs) have shown success in a diverse set of language inference and understanding tasks. The pre-training stage of LLMs looks at a large corpus of raw textual data. The BabyLM shared task compares LLM…
In-Context Learning (ICL) is a critical capability of Large Language Models (LLMs) as it empowers them to comprehend and reason across interconnected inputs. Evaluating the ICL ability of LLMs can enhance their utilization and deepen our…
The focus of this study is on Unsupervised Continual Learning (UCL), as it presents an alternative to Supervised Continual Learning which needs high-quality manual labeled data. The experiments under the UCL paradigm indicate a phenomenon…
Continual learning (CL) models are designed to learn new tasks arriving sequentially without re-training the network. However, real-world ML applications have very limited label information and these models suffer from catastrophic…
Large language models (LLMs) can adapt to new tasks via in-context learning (ICL) without parameter updates, making them powerful learning engines for fast adaptation. While extensive research has examined ICL as a few-shot learner, whether…
Curriculum learning (CL) is a training strategy that trains a machine learning model from easier data to harder data, which imitates the meaningful learning order in human curricula. As an easy-to-use plug-in, the CL strategy has…
Large Language Models (LLMs) serve as repositories of extensive world knowledge, enabling them to perform tasks such as question-answering and fact-checking. However, this knowledge can become obsolete as global contexts change. In this…
This paper introduces an interactive continual learning paradigm where AI models dynamically learn new skills from real-time human feedback while retaining prior knowledge. This paradigm distinctively addresses two major limitations of…
The ability to learn in dynamic, nonstationary environments without forgetting previous knowledge, also known as Continual Learning (CL), is a key enabler for scalable and trustworthy deployments of adaptive solutions. While the importance…