paper
In-Context Multiple Instance Learning
paperactiveprovisional
in-context-multiple-instance-learning-98c2058c·1 events·first seen 12d agoAliases: In-Context Multiple Instance Learning
Co-occurring entities
More like this (12)
Multiple Instance Learning (MIL)in-context learningMulti-Task LearningIn-Context Reward AdaptationLatent Context Language ModelsWhen English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context LearningReinforcement Learning Elicits Contextual Learning of Unseen Language TranslationMultimodal LearningClass-Incremental LearningIn-context Vector DistillationPose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject CustomizationOne-Shot Imitation Learning
Recent events (1)
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.