Who Speaks for the Pruned? Visual Token Pruning as Coverage Optimization

September 02, 2026 ยท Grace Period ยท ๐Ÿ› EMNLP 2026 main

โณ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Qingchan Zhu, Weihang You, Hanqi Jiang, Changdi Yang, Tianming Liu, Geng Yuan arXiv ID 2609.03158 Category cs.CV: Computer Vision Cross-listed cs.CL, cs.LG Citations 0 Venue EMNLP 2026 main
Abstract
Visual token pruning reduces the inference cost of vision-language models (VLMs), but most methods only ask which tokens to keep. This retained-token view can keep redundant high-scoring tokens while leaving discarded evidence without a close representative. We propose CoverPruner, a training-free pruner that asks the complementary demand-side question: after a token is removed, which surviving original token represents it for the target VLM? CoverPruner formulates pruning as Representational Coverage Maximization (RCM), covering the full projected visual-token set with query-weighted demand. It instantiates RCM with projector-space coverage and a lightweight first-layer attention probe. Across multiple VLM architectures and compression rates, CoverPruner achieves the best average accuracy among all compared methods, with the largest gains usually appearing under aggressive compression.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Computer Vision

๐ŸŒ… ๐ŸŒ… Old Age

Fast R-CNN

Ross Girshick

cs.CV ๐Ÿ› ICCV ๐Ÿ“š 27.7K cites 11 years ago