research
∙
03/10/2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
The conventional recipe for maximizing model accuracy is to (1) train mu...
share
research
∙
06/15/2021
Scene Transformer: A unified multi-task model for behavior prediction and planning
Predicting the future motion of multiple agents is necessary for plannin...
research
∙
12/15/2020
Mitigating bias in calibration error estimation
Building reliable machine learning systems requires that we correctly un...
research
∙
05/23/2017
