Preprint
Aug 2026
PixVL: Self-Supervised Training of Pixel-Level MLLMs via a Unified Mask--Text Consistency Cycle
PixVL is a self-supervised post-training framework that introduces a unified Mask--Text Consistency Cycle, enabling pixel-level MLLMs to generate and self-verify regional descriptions and learn from unlabeled data.
Yi-Cheng Xiao, Hao-Xuan Ma, Caorui Li et al.
· 0 citations