Thanks to visit codestin.com
Credit goes to github.com

Skip to content
View surajK610's full-sized avatar
7 followers · 4 following

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Achievements

Achievement: Pair ExtraordinaireAchievement: Pull Sharkx2Achievement: YOLOAchievement: QuickdrawAchievement: Arctic Code Vault Contributor

Block or report surajK610

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
surajK610/README.md

Hi there 👋, I'm Suraj

I am a 2024 graduate of Brown University with an M.S. in Computer Science and a B.Sc. in Applied Mathematics-Computer Science. I am interested in (1) solving complex engineering problems and (2) exploring fascinating mathematic/scientific ideas. My goal is to build algorithms that learn how to do useful things and are aligned with human values. I'm especially interested in Interpretability Research and GPU Optimization.

I currently work as a Quantitative Researcher at Point72 focused on using NLP research methods to find signal. I previously conducted research in the LUNAR Lab focused on learning dynamics of in context learning, investigating compositionality using causal interventions methods, mechanistic interpretability, and reinforcement learning from human feedback with Dr. Ellie Pavlick. I have previously collaborated with EleutherAI.

I've also been working on a couple of other ideas that I find interesting. Please check out my blog to learn more! 🐊

Need to reach me! Contact me at {username}@gmail.com.

Pinned Loading

  1. disentangled-learning-by-projection disentangled-learning-by-projection Public

    Jupyter Notebook

  2. simulated-annealing simulated-annealing Public

    Simulated Annealing Parallelization Experiments

    C++ 2

  3. dual-process-learning dual-process-learning Public

    Experiments from Dual Process Learning Paper

    Jupyter Notebook 2

  4. surajk610.github.io surajk610.github.io Public

    New Jekyll Style Website Based off of Al-Folio

    HTML 1

  5. APMA2822 APMA2822 Public

    from CPU optimizations to GPU programming

    C++ 1 1

  6. React-Lucidity React-Lucidity Public

    Front end interface for lucidity

    TypeScript