New paper on ArXiv from our lab - Elliot Creager and jörn jacobsen on the relationship between algorithmic fairness and OOD generalization

Our recent paper features a natural few-shot learning paradigm that continually introduce new objects in a sequence, such as when wandering through a new environment like walking room-to-room in a new house. arxiv.org/abs/2007.04546 Code & data: bit.ly/32wbK4x Mengye Ren

Check out Elliot Creager's poster session tomorrow at 12pm EST! #NeurIPS2020

Really excited to share our latest progress on few-shot classification on the Meta-Dataset benchmark (w/ Hugo Larochelle, Zemel Group and Vincent Dumoulin) that will appear in #ICML2021: arxiv.org/abs/2105.07029 Keep reading to find out more 👇🧵

Vision-Language-Action models are becoming the go-to architecture for robot generalization. But we know that to be reliable in high-stakes and open world environments, robots must “know what they don’t know,” so that they can recognize tasks where they are likely to fail.

Huge congratulations to Professor McKeown!!

New work on fair decision-making with LLMs from Zara Hall et al!