No AI summary available for this article.
Why It Matters
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We identify three key factors behind this degradation: text-guided selection bias, information loss from discarded tokens, and positional distortion caused by sequence compaction. Based on these observations, we propose \textbf{VPRune}, a training-free pre-LLM pruning framework consisting of visual-only diversity selection, similarity-guided token recycling, and position-preserving restoration. Expe...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.24485v1 · Indexed about 1 hour ago