menu MENU

Spotlight paper at NeurIPS

Zeyu Song and Dogyoon Song in front of their poster
Zeyu Song (left) and Dogyoon Song in front of their spotlight poster at neurIPS.

Our paper on recalibration of classifers was selected as a Spotlight paper at NeurIPS this year. NeurIPS is the most popular and competitive conference in AI and only 3% of submissions were selected for Spotlight this year.  The paper proposes a new method with theoretical guarantees for adapting pretrained neural networks to a new domain not well represented in the pre-training set. The method is directly applicable the in-context learning problem of foundation models (large language models).

Z Sun, D Song and A Hero, “Minimum-Risk Recalibration of Classifiers,” Neural Information Processing Symposium (NeurIPS), New Orleans, to appear, Dec 2023. NSF IPA, ARO MSU, DOE ETI.