Skip to content
View Aaquib111's full-sized avatar
  • College Park, MD

Block or report Aaquib111

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
Aaquib111/README.md

Hi! I am a final year CS+Math student at the University of Maryland.

Currently, I am a Student Researcher at Google DeepMind, working on the Frontier Safety team to evaluate and forecast dangerous capabilities.

I am interested in technical AI safety, particularly in interpretability, evaluating for future risks, and scaling techniques for aligning AI models.

Languages

Top Langs

Pinned Loading

  1. edge-attribution-patching edge-attribution-patching Public

    Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"

    Jupyter Notebook 45 12

  2. Sparse-GPT-Finetuning Sparse-GPT-Finetuning Public

    Code for my ICLR 2024 TinyPapers paper "Prune and Tune: Improving Efficient Pruning Techniques for Massive Language Models"

    Jupyter Notebook 16 3

  3. paper-implementations paper-implementations Public

    A growing collection of AI/ML implementations in C++, JAX and PyTorch

    Jupyter Notebook 1

  4. nanojax nanojax Public

    A small autodifferentiation library written in a JAX-like functional paradigm.

    Python 1

  5. magikarp01/mechanistic-unlearning magikarp01/mechanistic-unlearning Public

    Machine Unlearning via pruning/circuit discovery

    Jupyter Notebook 2 1

  6. java-algo-trading java-algo-trading Public

    Algorithmic Trading Platform in Java, based off the Alpaca API

    Java 4 1