Skip to content
View prateeky2806's full-sized avatar
46 followers · 3 following

Achievements

Achievement: Starstruckx2Achievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Achievements

Achievement: Starstruckx2Achievement: Pair ExtraordinaireAchievement: Arctic Code Vault ContributorAchievement: Pull Shark

Organizations

@pravega2k16

Block or report prateeky2806

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
prateeky2806/README.md

Hi there 👋

I work at Google DeepMind on Gemini.

Before this, I was doing pre-training at Meta, specifically incorporating RL/thinking in pre-training, architectures, and data constraint scaling (looping/pausing) with Mike Lewis and Sharan Narang. I also spent a year working part-time at Google DeepMind on modular post training methods with Jonathan Lai, Tsendsuren, Tu Vu, and Alexandra Chronopoulou.

I finished my PhD at UNC Chapel Hill advised by Colin Raffel and Prof. Mohit Bansal.

Previously, I have worked at Microsoft Research Redmond with Subhabrata Mukherjee, Ahmed H. Awadallah, and Amazon AWS AI Labs with Qing Sun. Before my PhD, I also worked at Microsoft Research India with Dr. Prateek Jain. I also worked full-time 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.

Popular repositories Loading

  1. ties-merging ties-merging Public

    Python 212 21

  2. ComPEFT ComPEFT Public

    Python 26

  3. exessnet exessnet Public

    Python 6

  4. EMC-COLS-recourse EMC-COLS-recourse Public

    Code for Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions

    Python 2 5

  5. Sentiment-Analysis-and-Classification-using-CNN-s Sentiment-Analysis-and-Classification-using-CNN-s Public

    Code and Material related to the project related to classification and Sentiment Analysis of Natural Language Text.

    Lua 1

  6. pravega2016 pravega2016 Public

    Code for the cultural, technical and science fest of Indian Institute of Science Bangalore. Coded and managed by Prateek Yadav

    JavaScript