做弱监督学习或医疗图像分析的团队，终于有了一个无需微调就能从少量标注包中学习的方案——单次前向传播搞定，值得直接试试。
多实例学习（MIL）处理的是包级别监督的问题，在计算病理学、卫星图像等领域有广泛应用。但现有算法在低标签数据场景下表现不佳，灵活模型容易过拟合，刚性模型难以适应新任务。本文提出一种基于Perceiver架构的上下文学习器，在合成数据上预训练后，仅需少量标注包即可解决新任务，推理时单次前向传播完成，无需梯度更新。研究设计了多种合成数据生成器，它们捕获互补的归纳偏置，混合预训练模型在12个MIL基准上平均性能最优，超越需要任务特定训练的监督基线。
In-Context Multiple Instance Learning
Multiple Instance Learning (MIL) addresses problems where supervision is available at the level of bags of instances and has been successfully applied in fields ranging from computational pathology to satellite imagery. Nevertheless, existing algorithms struggle in the low-label regime that characterizes many real-world applications. Flexible models overfit and rigid ones fail to adapt to the task at hand. We show that pretraining an in-context learner with a Perceiver-style architecture on synthetic data yields a model that can solve new tasks from a handful of labeled bags. At inference time, classification happens in a single forward pass and requires no gradient updates. We propose and investigate different synthetic data generators for bag-structured data and find that they capture complementary inductive biases. A model pretrained on a mixture of these generators inherits their per-task strengths and achieves the best average performance across twelve MIL benchmarks, outperforming supervised baselines that require task-specific training.