This README is mainly for how to reproduce MetaICL and Channel MetaICL in the paper, but also describe how to reproduce our baselines, including Multi-task zero-shot and various raw LM methods. All ...

In machine learning, it is generally assumed that the training samples are Independent and Identically Distributed (IID). As far as the sequence data is concerned, this isn’t always true. If the ...

Chengshu Li, Jacky Liang, Andy Zeng, Xinyun Chen, Karol Hausman, Dorsa Sadigh, Sergey Levine, Li Fei-Fei, Fei Xia, Brian Ichter [pdf], 2023.12.7 ...