Kaichen Li

@kaichen-li · 1 works

Researcher working on multimodal continual learning for vision-language models.

Recent posts by Kaichen Li

• A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-Training - In this paper, we explore a novel task of Multimodal Unsupervised Continual Post-Training (MU-CPT), enabling deployed MLLMs to continually evolve from streaming unlabeled data. Existing unsupervised… · Paper · arxiv.org