AI 中文总结
研究针对测试时视觉语言模型性能问题，从惩罚似然估计角度提出具有动态收缩的冯·米塞斯-费舍尔混合模型（MOON），该模型基于分布混合建模，能动态调整收缩强度处理不平衡，无需训练和特定超参，实验验证其性能和效率优势。
AI 中文摘要
一系列方法旨在提高视觉语言模型（VLM）在测试时的性能。其中，转导因其强大的兼容性和效率成为一种有前景的范式。然而，现实评估常涉及高度不平衡的类别分布，导致性能下降甚至崩溃。本文从惩罚似然估计（PLE）角度系统重新审视转导，表明带有KL散度锚定项的PLE自然会在先验锚和经验估计之间产生自适应收缩行为。基于此，我们提出具有动态收缩的冯·米塞斯-费舍尔混合模型（MOON）。MOON基于冯·米塞斯-费舍尔分布混合构建，在单位超球面上对特征表示建模。为处理不平衡，MOON在实例和类别级别使用零样本先验动态调整收缩强度，抑制不可靠分配，防止异常类的有害更新，减轻负迁移。MOON与模型无关、无需训练且无需特定任务超参数调整。大量实验进一步验证了MOON在性能和效率上的优势。
英文摘要
A range of methods aim to enhance the performance of vision-language models (VLMs) at test time. Among them, transduction has emerged as a promising paradigm due to its strong compatibility and efficiency. However, realistic evaluations often involve highly imbalanced class distributions, which cause performance degradation or even collapse. In this work, we systematically revisit transduction from the perspective of penalized likelihood estimation (PLE), showing that PLE with a KL-divergence anchor term naturally yields an adaptive shrinkage behavior between prior anchors and empirical estimates. From this viewpoint, the brittleness of transductive methods can be attributed to the absence of anchoring mechanism and static modeling of the shrinkage strength. Therefore, we propose Mixture of Von Mises-Fisher Models with Dynamic Shrinkage (MOON). MOON is built upon a mixture of von Mises-Fisher distributions to model feature representations on the unit hypersphere. To handle imbalance, MOON dynamically adjusts the shrinkage strength using zero-shot priors at both instance and class levels. Thus, it suppresses unreliable assignments and prevents harmful updates from outlier classes, thereby mitigating negative transfer. MOON is model-agnostic, training-free, and requires no task-specific hyperparameter tuning. Extensive experiments further validate the advantage of MOON in both performance and efficiency. Our code is available at https://github.com/walawalagoose/MOON
CommentsAccepted by ICML 2026
Journal refICML 2026
