While Infinia ML is focused on making business impact in machine learning, our commitment to academic research keeps us on technology’s cutting edge. Our team of machine learning experts have earned 7 PhDs and authored almost 600 published papers.

These are the papers published co-authored by Research Scientist Hongteng Xu under the Infinia ML name:

Topic-Guided Variational Autoencoders for Text Generation

PoPPy: A Point Process Toolbox Based on PyTorch

Distilled Wasserstein Learning for Word Embedding and Topic Modeling

Conference on Neural Information Processing System (NIPS), 2018

Acceptance Rate: ~22%

Quaternion Convolutional Neural Networks

The European Conference on Computer Vision (ECCV), 2018

Acceptance Rate: ~25%

Predicting Smoking Events with a Time-Varying Semi-Parametric Hawkes Process Model

The Conference on Machine Learning for Healthcare, 2018

Learning Registered Point Processes from Idiosyncratic Observations

The International Conference on Machine Learning (ICML), 2018

Acceptance Rate: 25%

Flexible Network Binarization with Layer-wise Priority

The International Conference on Image Processing (ICIP), 2018.

Online Continuous-Time Tensor Factorization Based on Pairwise Interactive Point Processes

The International Joint Conference on Artificial Intelligence (IJCAI-ECAI), 2018

Oral, Acceptance Rate: 20.4%

Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2018

Benefits from Superposed Hawkes Processes

The 21st International Conference on Artificial Intelligence and Statistics (AISTATS), 2018

Acceptance Rate: 33.2%