Prateek Yadav
Gemini @Google Deepmind, Past: Pre-training@Meta, ML PhD @ UNC Chapel Hill and Google Deepmind, Microsoft Research, Amazon AWS, IIT Madras, and IISc
- Role
- Senior Research Scientist at Google DeepMind
- Location
- Chapel Hill, NC, US
- LinkedIn followers
- 500 followers
About Prateek Yadav
Hey! I am a Ph.D. student at the MURGe-Lab at the University of North Carolina - Chapel Hill, where I work with Prof. Mohit Bansal and Prof. Colin Raffek. My research goal is to make deep learning models learn continually and generalize to multiple domains. I am interested in efficient methods that lead to generalization and exploiting sparsity, memory, and mixture-of-expert models for continual learning.Previously, I have worked on a diverse set of topics – 1) Interpretability, 2) compositional reasoning in NLP, 3) deep learning methods for Graph and Hypergraph structured data and their application to NLP, 4) estimated and controlled for uncertainty in the learned representations from these methods, and 5) worked on Bayesian modeling of temporal data.Over the past few years, I have been fortunate to work with Ming Tan, Qing Sun, and Xiaopeng Li at Amazon AWS AI Labs, with Prof. Partha Talukdar at MALL-Lab at Indian Institute of Science (IISc) Bangalore, with Dr. Prateek Jain at Microsoft Research India and with Prof. Arun Rajkumar at Indian Institute of Technology, Madras. I also worked for a year with some amazing people at LinkedIn AI Bangalore. Before all this, I completed my undergraduate degree in pure mathematics in 2018 from IISc Bangalore where I was supervised by Prof. Partha Talukdar.
Experience
Senior Research Scientist
Feb 2026 — Present · Mountain View, CA, US
Education
Indian Institute of Science (IISc)
Bachelor of Science - BS, Mathematics and Computer Science
2014 — 2018
The University of North Carolina at Chapel Hill
Master of Science - MS, Computer Science
The University of North Carolina at Chapel Hill
Doctor of Philosophy - PhD, Computer Science
St. Anselm's North City School , Jaipur
Middle School
2001 — 2012
Step By Step High School , Jaipur
High School, Physics, Chemistry and Mathematics
2012 — 2014
Skills
- Data Structures
- Research
- Linux
- Time Series Analysis
- Tensorflow
- Financial Analysis
- C++
- Theano
- Python
- Opencl
- Latex
- Algorithm Design
- Javascript
- Scikit-Learn
- Knowledge Graphs
- R
- Cuda
- Data Analytics
- Opencv
- Html
- Computer Vision
- Cascading Style Sheets (Css)
- Natural Language Processing
- Lua
- Data Analysis
- Visual Studio
- Deep Learning
- Torch
Find verified contacts for anyone on LinkedIn
Unifers gives sales teams verified emails and direct dials, enriched profiles, and outreach that lands in the inbox.
Free plan included · No credit card required
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.