No AI summary available for this article.
Why It Matters
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.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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 post-training methods for MLLMs typically optimize target tokens uniformly, overlooking their heterogeneous visual dependence (VD). However, we reveal that token-level VD is crucial for MU-CPT. Specifically, its structural distortion serves as an indicator of cross-modal catastrophic forgetting, and its inherent heterogeneity acts as a compass to guide new-task learning. Leveraging this property, w...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2608.26095v1 · Indexed 4 days ago