research
∙
08/14/2023
CausalLM is not optimal for in-context learning
Recent empirical evidence indicates that transformer based in-context le...
share
research
∙
11/22/2022
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
Recent research in robust optimization has shown an overfitting-like phe...
research
∙
03/10/2022
PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks
With the increasing abundance of pretrained models in recent years, the ...
research
∙
05/28/2021
Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning
Despite recent advances in its theoretical understanding, there still re...
research
∙
10/13/2020
Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance
Recent advances in automatic evaluation metrics for text have shown that...
research
∙
11/21/2019
Reinforcing an Image Caption Generator Using Off-Line Human Feedback
Human ratings are currently the most accurate way to assess the quality ...
research
∙
09/08/2019
Quality Estimation for Image Captions Based on Large-scale Human Evaluations
Automatic image captioning has improved significantly in the last few ye...
research
∙
06/20/2019