Vijay Daita

vijayd2@illinois.edu

I'm an undergraduate student at UIUC studying Computer Science and Economics. I'm broadly interested in agent-based assistants, SE, and MLSys. Over the past few years, I've worked on the following projects:

LLMs for Software Engineering

  • Developed a website that allowed users to chat with the documentation of a given library using Next.jsvdaita/repohelper
    • Created scrapers that used search results to get content from any website (currently disabled for cost)
  • Built a command-line utility using Typer for people to modify their code with LLMs, expanding on Aider by using multi-step reflection and explorationvdaita/superdocs-python
  • Built a VSCode extension using React, and created a backend using serverless functions and Postgres to authenticate users and manage integration of other servicesvdaita/superdocs
  • Worked on an evaluation of LLM understanding of code over long contextsevalplus/repoqa

LLM Optimization

  • Optimized speculative decoding for code editing using HuggingFace Transformers and PyTorch with researchers at UIUC, and integrated it into the custom GUIx/twitter
  • Wrote and evaluated custom CUDA kernels for block-sparse attention and flash-decodingvdaita/ece408-final-project
  • Wrotean essay on a training-free approach to improving pooling methods when computing a coarse attention map for block-sparse attention

NLP for Information Retrieval and Analysis

  • An assistant for retrieving and summarizing papers from Arxivvdaita/arxiv-assistant
  • Research assistantship at the Gies School of Business
    • Automated quote extraction to provide qualitative evidence
    • Using named entity recognition and LLM-based few-shot classification for quantitatively understanding industry trends and company priorities
    • Using sentence and word embeddings to understand patterns of nationalistic sentiment in company websites over time.

Other

  • Working as a Course Assistant for CS374 (Introduction to Algorithms and Models of Computation)
  • Worked as a full-stack developer at the Carle School of Medicine, where I worked on integrating LLMs with a Next.js apps to autogenerate quizzes for patients based on their medication.
  • Set up LongLakeTech.com (sold in August 2024), selling frontend development and data science services

Posts

January 4, 2025

Selecting Blocks for Block-Sparse Attention

June 10, 2024

RepoQA: Evaluating Long-Context Code Understanding