← 研踪 PaperTrailarXiv:2610.38303 · v1
Don't Ask the LLM: Visual Token Pruning with Spectral Structure and Semantic Relevance
首次提交 2026-10-28 13:39
版本更新 2026-10-28 13:39
雷达观测 2026-10-30 10:22
摘要
Large vision-language models (LVLMs) represent images and videos as long visual-token sequences, substantially increasing inference costs. These costs motivate visual-token pruning, whose effectiveness depends on both what signal is used for selection and when that signal becomes available. Our analysis reveals complementary limitations: visual-side [CLS] attention produces scattered, background-biased selections under aggressive compression, while stronger query-conditioned signals become available after substantial computation within the large language model (LLM). This raises a natural question: can structurally coherent, query-aware token selection be performed before consulting the LLM? We therefore propose ST-Pruner (Spectral-Textual Pruner), a training-free framework for pre-LLM visual-token selection. It combines attention-independent spectral saliency with inverted patch-text similarity through parameter-free multiplicative fusion. Across diverse LVLMs, ST-Pruner retains over 95% of full-token performance using at most 11.1% of visual tokens and achieves a 3.2x end-to-end speedup on LLaVA-NeXT. Code is available at https://github.com/sejong-rcv/ST-Pruner.
作者备注：Accepted to WACV 2027. 19 pages (10 pages main paper, 9 pages supplementary material)
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-10-28 13:39 · 最新观测版本
Don't Ask the LLM: Visual Token Pruning with Spectral Structure and Semantic Relevance
Large vision-language models (LVLMs) represent images and videos as long visual-token sequences, substantially increasing inference costs. These costs motivate visual-token pruning, whose effectiveness depends on both what signal is used for selection and when that signal becomes available. Our analysis reveals complementary limitations: visual-side [CLS] attention produces scattered, background-biased selections under aggressive compression, while stronger query-conditioned signals become available after substantial computation within the large language model (LLM). This raises a natural question: can structurally coherent, query-aware token selection be performed before consulting the LLM? We therefore propose ST-Pruner (Spectral-Textual Pruner), a training-free framework for pre-LLM visual-token selection. It combines attention-independent spectral saliency with inverted patch-text similarity through parameter-free multiplicative fusion. Across diverse LVLMs, ST-Pruner retains over 95% of full-token performance using at most 11.1% of visual tokens and achieves a 3.2x end-to-end speedup on LLaVA-NeXT. Code is available at https://github.com/sejong-rcv/ST-Pruner.
查看此版本解读 →查看此版本原文 ↗