AI RESEARCH
PixelPrune: Pixel-Level Adaptive Visual Token Reduction via Predictive Coding
arXiv CS.AI
•
ArXi:2604.00886v1 Announce Type: cross Document understanding and GUI interaction are among the highest-value applications of Vision-Language Models (VLMs), yet they impose exceptionally heavy computational burden: fine-grained text and small UI elements demand high-resolution inputs that produce tens of thousands of visual tokens. We observe that this cost is largely wasteful -- across document and GUI benchmarks, only 22--71\% of image patches are pixel-unique, the rest being exact duplicates of another patch in the same image.