I just learned my postdoc roommate Yisong Yue from Caltech released a new interesting paper: Factorized Variational Autoencoders for Modeling Audience Reactions to Movies: a joint work with Disney Research, published @ CVPR 2017.
Another interesting paper: Accelerating Innovation Through Analogy Mining, just received the best paper award at KDD 2017. The paper is by Dafna Shahaf who studied with me at CMU and her student Tom Hope.
An earlier related work of Dafna is a paper for identifying humor in cartoon captions.
an source for gradient boosting. It seems to compete with XGBoost with the claim that it supports categorical variables as well. (In GraphLab Create we had an extended XGBoost with categorical variable support).