In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

Active Testing: Sample-Efficient Model Evaluation

Structured object-aware physics prediction for video modeling and planning