SCoRe：面向视觉语言模型视觉词元剪枝的显著性-覆盖度约减
SCoRe: Salience-Coverage Reduction for Vision Token Pruning in Vision-Language Models
把视觉编码器内的词元剪枝从解耦启发式规则重构为加权 k-Center 覆盖优化，用统一的代表性分数贪心选点，可直接替换 LLaVA 类 LVLM 视觉端的 token 压缩模块，在 94.4% 剪枝率下保住 95% 性能。
原文依据 SCoRe constructs the final token set greedily: at each iteration, it selects the token that maximizes the unified representativeness score
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大型视觉语言模型（LVLM）的沉重计算负担主要源于其视觉编码器生成的长视觉词元序列。为缓解这一问题，近期工作转向在视觉编码器内部进行词元剪枝。然而，我们观察到这些方法大多依赖一种次优的解耦启发式方法。该策略在概念上存在缺陷：它容易发生采样坍缩，无法从根本上消除词元冗余，并且倾向于系统性地丢弃次要但重要的语义簇。针对这一局限，本文将视觉词元剪枝形式化为一个统一的代表性优化问题。我们提出 SCoRe（显著性-覆盖度约减），一种在理论上以加权 k 中心问题为基础的统一优化方法。SCoRe 以贪心方式构造最终词元集合：在每次迭代中，它选择使统一代表性得分最大的词元，从而优化全局代表性。大量实验表明，SCoRe 在多个基准上取得了最优性能。值得注意的是，在计算开销可忽略的情况下，我们的方法将词元减少 94.4%，同时保留完整性能的 95%。
英文原文摘要 1264 字符
The heavy computational burden of Large Vision-Language Models (LVLMs) stems primarily from the lengthy visual token sequences generated by their vision encoders. To mitigate this, recent work has shifted towards pruning tokens within the vision encoder. However, we observe that these methods predominantly rely on a suboptimal decoupled heuristic method. This strategy is conceptually flawed: it is prone to sampling collapse, fails to fundamentally eliminate token redundancy, and tends to systematically discard secondary yet important semantic clusters. Addressing this limitation, this paper proposes to formalize visual token pruning as a unified Representativeness Optimization Problem. We introduce SCoRe (Salience-Coverage Reduction), a unified optimization method theoretically grounded in the Weighted k-Center Problem. SCoRe constructs the final token set greedily: at each iteration, it selects the token that maximizes the unified representativeness score, thereby optimizing global representativeness. Extensive experiments demonstrate that SCoRe achieves State-of-the-Art (SOTA) performance across multiple benchmarks. Notably, with negligible computational overhead, our method reduces tokens by 94.4% while retaining 95% of the full performance.