Shankar Padmanabhan | My Homepage (original) (raw)

Hi! I am a first year PhD student at Cornell University. I'm gratefully supported by an NSF GFRP Fellowship.

My research is in Natural Language Processing. At the moment, I am interested in empirical methods to improve our understanding of LMs. In the past, I also worked on continual learning and model editing for LMs.

I obtained my undergraduate degree at UT Austin, where I was first introduced to NLP and was fortunate to work with Prof. Eunsol Choi, Prof. Greg Durrett, and Prof. Richard Tsai.

Publications

• Propagating Knowledge Updates to LMs Through Distillation. NeurIPS, 2023

Shankar Padmanabhan, Yasumasa Onoe, Michael J.Q. Zhang, Greg Durrett, Eunsol Choi.

• Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge. ACL, 2023. Yasumasa Onoe, Michael J.Q. Zhang, Shankar Padmanabhan, Greg Durrett, Eunsol Choi.

Preprints

• Optimal Placement of Public Electric Vehicle Charging Stations Using Deep Reinforcement Learning. arXiv, 2021.Shankar Padmanabhan*, Aidan Petratos*, Allen Ting*, Kristina Zhou, Dylan Hageman, Jesse Pisel, Michael Pyrcz.

Hobbies

In my free time, I am passionate about learning languages. Through a small amount of "supervised training" (Duolingo) and a large amount of "unsupervised training" (native media), I have become a fluent speaker of Spanish, and I am learning French and Tamil as well. Additionally, I enjoy ultimate frisbee and calisthenics.