New York University
Incremental Skill Discovery for RL Agents
I’m working in the CILVR Lab with Prof. Lerrel Pinto on expanding Citation: Shafiullah et. al., (2022) Shafiullah, Nur Muhammad & Lerrel Pinto (2022). One After Another: Learning Incremental Skills for a Changing World. arXiv preprint arXiv:2203.11176. https://arxiv.org/abs/2203.11176 ’s incremental skill discovery framework to manipulation environments like AllegroHand.
New York University
Speech Recognition for Mandarin Conversations
I’m working with Prof. Michael Picheny on DARPA’s CCU Program to improve speech recognition systems for conversational Mandarin, primarily on the AISHELL4 dataset (Citation: Fu et. al., 2021 Fu, Yihui, Luyao Cheng, Shubo Lv, Yukai Jv, Yuxiang Kong, Zhuo Chen, Yanxin Hu, Lei Xie, Jian Wu, Hui Bu & others (2021). AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenario. arXiv preprint arXiv:2104.03603. https://arxiv.org/abs/2104.03603 ).
Bust Replacement on Photorealistic Model Images
I worked with StyleGANs to generate bust-level crops of photorealistic model images, making use of techniques like GAN inversion and style mixing. I also used classical methods like MLS (Citation: Schaefer et. al., 2006 Schaefer, Scott, Travis McPhail & Joe Warren (2006). Image Deformation Using Moving Least Squares. In ACM SIGGRAPH 2006 Papers. (pp. 533–540). https://dl.acm.org/doi/10.1145/1179352.1141920 ) to create an end-to-end pipeline for bust replacement upto 1024px.
Neural Conversational Question Answering
I worked with Danish Contractor on improving question answering systems on the ShARC dataset (Citation: Saeidi et. al., 2018 Saeidi, Marzieh, Max Bartolo, Patrick Lewis, Sameer Singh, Tim Rocktäschel, Mike Sheldon, Guillaume Bouchard & Sebastian Riedel (2018). Interpretation of Natural Language Rules in Conversational Machine Reading. arXiv preprint arXiv:1809.01494. https://arxiv.org/abs/1809.01494 ). This led to a patent (US 16/892805), and a paper (Citation: Verma et. al., 2020 Verma, Nikhil, Abhishek Sharma, Dhiraj Madan, Danish Contractor, Harshit Kumar & Sachindra Joshi (2020). Neural Conversational QA: Learning to Reason vs Exploiting Patterns. Association for Computational Linguistics. https://doi.org/10.18653/v1/2020.emnlp-main.589 ).
Code to Natural Language
[Report] I worked with Navin Goyal on techniques to describe code (SQL Queries and
bash commands in particular) in natural language as part of my undergrad thesis.
[Report] I worked on improving techniques to generate answerable questions from text.