AI 中文总结
研究高分辨率视觉语言模型中令牌减少问题。提出GOTS方法，通过所选跨度互补性，无训练且与查询无关，每步选正交最大剩余能量令牌。在多主干和基准测试中性能优，还减少模型端首次令牌时间。
AI 中文摘要
现代视觉语言模型（VLM）越来越依赖动态或高分辨率视觉编码，产生数千个视觉令牌，大幅增加下游语言模型推理成本。现有令牌减少方法通过令牌重要性、查询相关性等评估令牌效用。本文关键见解是通过所选跨度互补性看待视觉令牌减少，提出无训练且与查询无关的贪婪正交令牌选择（GOTS）方法。每一步选择与当前保留跨度正交的具有最大剩余能量的令牌，该规则精确最大化候选添加中的一步增强Gram行列式。在五个高分辨率VLM主干和十一个基准测试中，GOTS平均性能保留率高于最强基线，且在考虑选择开销后减少了模型端首次令牌时间。
英文摘要
Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream language-model inference cost. Existing token-reduction methods assess token utility through token-wise importance, query relevance, coverage, pairwise diversity, or subset-level objectives. Our key insight is to view visual token reduction through selected-span complementarity: instead of scoring a token in isolation or through pairwise relations, we assess how much of its feature is orthogonal to the span of the already retained subset. Based on this perspective, we propose Greedy Orthogonal Token Selection (GOTS), a training-free and query-agnostic method. At each step, GOTS selects the token with the largest residual energy orthogonal to the current retained span. This rule exactly maximizes the one-step augmented Gram determinant among candidate additions, giving each greedy step a precise local geometric guarantee for subset expansion. Across five high-resolution VLM backbones from the Qwen-VL and InternVL families and eleven diverse benchmarks, GOTS achieves higher average performance retention than the strongest evaluated baselines, and a controlled OCRBench study shows that it reduces model-side time-to-first-token after accounting for selection overhead. Code is available at https://github.com/newLLing/GOTS.
