Abhishek Kumar

Abhishek Kumar 

Machine Learning, Artificial Intelligence
IBM T.J. Watson Research Center
Yorktown Heights, NY 10598


Contact: myfirstname @ umiacs.umd.edu, myfirstname @ inductivebias.net

I am a researcher at IBM Research AI, working broadly in the area of machine learning and artificial intelligence. Among many other topics, I am particularly interested in the problem of learning with limited labeled data via invariant/disentangled representations, semi-supervised and transfer learning, deep generative models (implicit and explicit), few-shot learning leveraging multiple tasks, universal representations, injecting external/auxiliary knowledge, etc. I am also highly interested in machine learning for natural language understanding and computer vision problems.

Before joining IBM, I graduated with a Ph.D. from Department of Computer Science at University of Maryland in 2013 where my advisor was Hal Daumé III. I have also worked on robust automatic speech recognition during my Masters at CRSS, advised by John H. L. Hansen.