Hi! My name is Nikhil and this is my home on the internet.

I’m currently building LLM based systems for document understanding at Roots Automation. I graduated from NYU’s Courant Institute with a Masters in Computer Science, where I was a part of the CILVR group working with Prof. Lerrel Pinto and Prof. Rob Fergus. My research culminated into a thesis on Offline Reinforcement Learning for Imperfect Information Games.

Before NYU, I was working on novel techniques for conversational question answering with Danish Contractor and his team at IBM Research India. Subsequently, I also worked with GANs for photorealistic image generation at Flixstock. I hold a bachelor’s degree from BITS Pilani in Electrical Engineering, where I got the opportunity to write a thesis as a Research Intern at Microsoft Research India. I worked with Navin Goyal on translating code to natural language. For more information, you can have a look at my resume.

Publications

[Abstract] Neural Conversational QA: Learning to Reason vs Exploiting Patterns
Nikhil Verma, Abhishek Sharma, Dhiraj Madan, Danish Contractor, Harshit Kumar, Sachindra Joshi
Paper published at EMNLP 2020

[US 16/892805] Generating Dialog System Workspaces
Danish Contractor, Nikhil Verma, Harshit Kumar and Sachindra Joshi
Patent filed with the US Patent and Trademark Office

Open Source

[GitHub] SHIS: Simple HTTP Image Server
A drop-in replacement for python -m http.server, albeit for images.