Subject-Centric Progressive Visual Token Reduction

Focus-then-Context: Subject-Centric Progressive Visual Token Reduction for Vision-Language Models

arXiv:2605.20950v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) face a bottleneck of prohibitive computational costs arising from massive visual token sequences during inference. Existing vision token reduction methods alleviate this burden, but they unintentionally preserve the isolated visual subject strictly aligned with the user's query, which fails to substantially explore salient subjects and their contextual relationships. In this paper, we propose SPpruner, a...