Entity · paper

In-Context Multiple Instance Learning

paperactivein-context-multiple-instance-learning-98c2058c·1 events·first seen Jun 5, 2026

Aliases: In-Context Multiple Instance Learning

Co-occurring entities

More like this (12)

Multi-Task Bayesian In-Context Learning Multiple Instance Learning (MIL)in-context learning Multi-Task Learning Induction in Both Directions: A Mechanistic Analysis of In-Context Learning in Masked Diffusion Language Models In-Context Reward Adaptation Latent Context Language Models When English Isn't the Best Teacher: Source Language Effects in Cross-Lingual In-Context Learning Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification Extending LLM Context via Associative Recurrent Memory Multimodal Learning

Recent events (1)

4arXiv · cs.AI·Jun 5, 2026·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.

Evaluation and Benchmarking In-Context Multiple Instance Learning Perceiver IO