Kumar Krishna Agrawal

I am a Resident at Google Brain as part of the Residency Program. My research interests lie in the intersection of Machine Learning and Robotics. I am passionate about developing algorithms for agents which can meaningfully interact with their environment.

I graduated from IIT-Kharagpur in 2017 with Bachelors and Masters in Mathematics and Computing. In the summer of 2016, I was a research intern at the MILA Lab under the supervision of Prof. Yoshua Bengio. Prior to that, I was a part of the Summer Research Expeditions, 2015 at Johns Hopkins University, where I worked under Prof. Raman Arora.

blog / github

Kumar Krishna Agrawal

I am broadly interested in learning for robotics. More specifically, I am interested in enhanced perception and communication, to allow robots to replicate and generate complex behaviour.

Playing with Embeddings : Evaluating embeddings for Robot Language Learning through MUD Games
Anmol Gulati*, Kumar Krishna Agrawal*
EMNLP Workshop on Evaluating Vector Space Representations for NLP, 2017
[paper] [slides]

Recurrent Memory Addressing for describing videos
Arnav Jain*, Abhinav Agarwalla*, Kumar Krishna Agrawal*, Pabitra Mitra
CVPR Workshop on Deep Learning in Computer Vision, 2017

Generative Adversarial Motion to Image Synthesis
Arna Ghosh*, Kumar Krishna Agrawal*
ECCV Workshop on Artificial and Biological Vision, 2016

(This, is much more classy)