跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.19745 · v2

TIVS: Mapping the Sensitivity Landscape of Visual Token Transformations in MLLMs

首次提交 2026-11-15 11:13
版本更新 2026-11-17 11:16
雷达观测 2026-11-18 19:43
arXiv ↗PDF ↗

摘要

Recent efforts to improve the efficiency of multimodal large language models (MLLMs) have explored visual token pruning, quantization, and feature compression. However, the properties that determine whether transformed visual tokens remain usable by a frozen decoder are not well characterized. We introduce \textbf{TIVS (Token Identity Versus Statistics)}, a training-free intervention framework that separately studies sequence permutation, token retention, numerical precision, and statistical replacement under controlled conditions. On 192 POPE questions, three token permutations change TinyLLaVA accuracy by only −0.17-0.17 percentage points on average, while changing 4.69\% of individual predictions. Diagonal and rank-64 Gaussian replacements decrease accuracy by 25.0 and 28.1 points on the same subset. Further experiments with exact moment constraints, quantization error, token retention, and additional visual tasks reveal how strongly the effects depend on the original feature values and the evaluation setting. These findings provide an empirical basis for assessing visual token transformations in frozen MLLMs and designing more reliable multimodal interfaces.

作者备注:9 pages, 12 figures, 3 tables

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

仅对比实际观测的元数据,不代表 PDF 正文或实验变化。版本可能不连续;带删除线为移除,下划线为新增。

这两个版本的已观测标题、作者、分类、摘要和备注没有变化。正文是否变化请核对原文。

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。

v2 · 2026-11-17 11:16 · 最新观测版本

TIVS: Mapping the Sensitivity Landscape of Visual Token Transformations in MLLMs

Recent efforts to improve the efficiency of multimodal large language models (MLLMs) have explored visual token pruning, quantization, and feature compression. However, the properties that determine whether transformed visual tokens remain usable by a frozen decoder are not well characterized. We introduce \textbf{TIVS (Token Identity Versus Statistics)}, a training-free intervention framework that separately studies sequence permutation, token retention, numerical precision, and statistical replacement under controlled conditions. On 192 POPE questions, three token permutations change TinyLLaVA accuracy by only −0.17-0.17 percentage points on average, while changing 4.69\% of individual predictions. Diagonal and rank-64 Gaussian replacements decrease accuracy by 25.0 and 28.1 points on the same subset. Further experiments with exact moment constraints, quantization error, token retention, and additional visual tasks reveal how strongly the effects depend on the original feature values and the evaluation setting. These findings provide an empirical basis for assessing visual token transformations in frozen MLLMs and designing more reliable multimodal interfaces.

查看此版本解读 →查看此版本原文 ↗
v1 · 2026-11-15 11:13

TIVS: Mapping the Sensitivity Landscape of Visual Token Transformations in MLLMs

Recent efforts to improve the efficiency of multimodal large language models (MLLMs) have explored visual token pruning, quantization, and feature compression. However, the properties that determine whether transformed visual tokens remain usable by a frozen decoder are not well characterized. We introduce \textbf{TIVS (Token Identity Versus Statistics)}, a training-free intervention framework that separately studies sequence permutation, token retention, numerical precision, and statistical replacement under controlled conditions. On 192 POPE questions, three token permutations change TinyLLaVA accuracy by only −0.17-0.17 percentage points on average, while changing 4.69\% of individual predictions. Diagonal and rank-64 Gaussian replacements decrease accuracy by 25.0 and 28.1 points on the same subset. Further experiments with exact moment constraints, quantization error, token retention, and additional visual tasks reveal how strongly the effects depend on the original feature values and the evaluation setting. These findings provide an empirical basis for assessing visual token transformations in frozen MLLMs and designing more reliable multimodal interfaces.

查看此版本解读 →查看此版本原文 ↗