<ul><li>Recent advancements in Artificial Intelligence have led to the development of Multimodal Large Language Models (MLLMs).</li><li>Fine-tuning MLLMs for specific tasks often causes performance degradation in the model's prior knowledge domain, known as 'Catastrophic Forgetting'.</li><li>This review paper provides an overview and analysis of 440 research papers in the field of MLLM continual learning.</li><li>The paper discusses the challenges and future directions of continual learning in MLLMs, aiming to inspire future research and development in the field.</li></ul>

When Continue Learning Meets Multimodal Large Language Model: A Survey

Discover more