Almanac
paper

In-Context Multiple Instance Learning

paperactiveprovisionalin-context-multiple-instance-learning-98c2058c·1 events·first seen 12d ago

Aliases: In-Context Multiple Instance Learning

Co-occurring entities

More like this (12)

Recent events (1)

4arXiv · cs.AI·12d ago·source ↗

In-context learning applied to Multiple Instance Learning via Perceiver-style pretraining on synthetic data

A new arXiv preprint proposes pretraining an in-context learner with a Perceiver-style architecture on synthetic bag-structured data to solve Multiple Instance Learning (MIL) tasks from a handful of labeled bags at inference time, requiring no gradient updates. The authors evaluate several synthetic data generators and find that a mixture-pretrained model captures complementary inductive biases, outperforming supervised baselines across twelve MIL benchmarks. The work addresses the low-label regime common in domains like computational pathology and satellite imagery.