Ananya Kumar

TL;DR: This paper showed that fine-tuning can achieve worse accuracy than linear probing out-of-distribution (OOD) when the pretrained features are good and the distribution shift is large.

TL;DR: The scaling-binning calibrator is introduced, which first fits a parametric function to reduce variance and then bins the function values to actually ensure calibration, and estimates a model's calibration error more accurately using an estimator from the meteorological community.

TL;DR: The Holistic Evaluation of Language Models (HELM) as mentioned in this paper ) is a popular benchmark for language models, with 30 models evaluated on 16 core scenarios and 7 metrics, exposing important trade-offs.

TL;DR: It is proved the first non-vacuous upper bound on the error of self-training with gradual shifts, under settings where directly adapting to the target domain can result in unbounded error.

TL;DR: The authors provides a thorough account of the opportunities and risks of foundation models, ranging from their capabilities (e.g., language, vision, robotics, reasoning, human interaction) and technical principles(e. g.g. model architectures, training procedures, data, systems, security, evaluation, theory) to their applications.