Skip to content
View raishish's full-sized avatar
πŸ› οΈ
πŸ› οΈ

Highlights

  • Pro

Organizations

@vital2

Block or report raishish

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
raishish/README.md

Hi there πŸ‘‹, my name is Ashish Rai

I'm an applied AI researcher.

  • πŸ”¬ I’m currently working on understanding how information is stored and retrieved in discrete diffusion language models using ROME. Checkout πŸ”¬ discrete-diffusion-rome.
  • 🌱 I’m currently learning GPU programming (and re-learning C++) across different accelerator backends. Checkout πŸš€ unikernels.
  • πŸ§‘πŸ»β€πŸ’» I often contribute to open source and open science projects as well.
  • πŸ˜„ Pronouns: he/him

Catch me on:

Twitter     🌐 Website     LinkedIn

Notable Open Source Contributions

πŸ“ˆ GitHub Stats

GitHub stats

πŸ† GitHub Trophies

Your GitHub trophies

Pinned Loading

  1. arc-agi-vision arc-agi-vision Public

    A vision-based approach for ARC-AGI

    Jupyter Notebook 1

  2. simpleqa-hf simpleqa-hf Public

    SimpleQA Evaluation for Hugging Face Models

    Python 1

  3. video-prediction-segmentation video-prediction-segmentation Public

    Given n seed frames of a video, predict the next m frames.

    Python 2

  4. vqa-attention vqa-attention Public

    Comparing human attention vs attention in transformers for Visual Question Answering

  5. kalpanmukherjee/uLookup kalpanmukherjee/uLookup Public

    Select text on any website, right click and select 'ULookUp' and get realtime explainations. You know, like Apple's LookUp feature, but, Useful.

    JavaScript 1

  6. mcqa-artifacts mcqa-artifacts Public

    Forked from sleepingcat4/mcqa-artifacts

    Code for the paper "Artifacts or Abduction: How Do LLMs Answer Multiple-Choice Questions Without the Question?"

    Python 1