Continual Learning of Multimodal Large Language Models

We are an academic research group focused on Continual Learning for Multimodal Large Models (MLLMs). Led by Dr. Fei Zhu from the Centre for Artificial Intelligence and Robotics (CAIR) at the Hong Kong Institute of Science & Innovation, Chinese Academy of Sciences. We aim to construct a continuously evolving multimodal large language model (MLLM) system.

If you are interested in our community and want to join us, feel free to contact us on GitHub or by email.

• We are looking for contributors, collaborators, and partners to build a better MLLM-CL community.
• We are also looking for sponsors to support our community and projects. If you are interested in sponsoring us, please contact us.

Here are our related works:

MLLM-CL: Continual Learning for Multimodal Large Language Models

VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?