LGCVJun 16, 2025

Continual Learning for Generative AI: From LLMs to MLLMs and Beyond

arXiv:2506.13045v410 citationsh-index: 34Has Code
Originality Synthesis-oriented
AI Analysis

It provides a comprehensive overview for researchers and practitioners working on scalable and adaptable generative AI systems, but it is incremental as it synthesizes existing methods rather than introducing new ones.

This paper surveys continual learning methods for generative AI models, addressing the problem of catastrophic forgetting where models lose performance on old tasks when learning new ones, and categorizes approaches into architecture-based, regularization-based, and replay-based paradigms.

The rapid advancement of generative models has empowered modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains. However, these models are fundamentally constrained by \emph{catastrophic forgetting}, \ie~a persistent challenge where models experience performance degradation on previously learned tasks when adapting to new tasks. To address this practical limitation, numerous approaches have been proposed to enhance the adaptability and scalability of generative AI in real-world applications. In this work, we present a comprehensive survey of continual learning methods for mainstream generative AI models, encompassing large language models, multimodal large language models, vision-language-action models, and diffusion models. Drawing inspiration from the memory mechanisms of the human brain, we systematically categorize these approaches into three paradigms: architecture-based, regularization-based, and replay-based methods, while elucidating their underlying methodologies and motivations. We further analyze continual learning setups for different generative models, including training objectives, benchmarks, and core backbones, thereby providing deeper insights into the field. The project page of this paper is available at https://github.com/Ghy0501/Awesome-Continual-Learning-in-Generative-Models.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes