Skip to content

ctrl-gaurav/ctrl-gaurav

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

32 Commits
 
 
 
 

Repository files navigation

Hi there, I'm Gaurav Srivastava

Visitor count

I'm a Master's student in Computer Science at Virginia Tech (Graduating May 2026), and fortunately advised by Dr. Xuan Wang. I am also affiliated with the Sanghani Center for Artificial Intelligence and Data Analytics.

Prior to joining Virginia Tech, I got my Bachelor's degree in Computer Science from Manipal University Jaipur in July 2023. During my Bachelor's program, I was fortunate to be supervised by Dr. Nitesh Pradhan and worked with Dr. Vijaypal Singh Dhaka and Dr. Mahesh Jangid. I was also the President's Gold Medalist for Excellence in Research. After that I worked at Dell Technologies for 1 year as a Machine Learning Engineer. Before that, I spent 6 months at Swiggy's Applied Research (Computer Vision) team.

Research  Interests

I work on improving small language models in reasoning—pushing lightweight LMs to think deeper, act smarter, and collaborate like expert teams. My research spans natural‑language processing, complex reasoning, and model efficiency, all aimed at creating efficient, low‑cost AI systems. My current focus areas include:

  • 🧠 Complex Reasoning in Large & Small Language Models (LLMs & SLMs): I study emergent reasoning, chain‑of‑thought, and which facets of reasoning are kept or lost after compression—revealing when  and  why small models succeed or fail.
  • 🚀 Multi‑Agent Debate & Self‑Evolution: I design systems where multiple LMs critique, refine, and distill each other’s outputs. Iteratively fine‑tuning the resulting “debate traces” lets a single model self‑evolve without human‑labeled data.
  • 🧠 Overthinking in Basic Reasoning: I also study when language models overthink problems that humans solve instinctively. I developed LLMThinkBench, a framework that measures when—and why—LLMs overthink straightforward math and logical reasoning tasks.

LinkedIn   Portfolio   Gmail

🛠️ Tech Stack & Tools

Here are some of the technologies I actively work with:

Python   PyTorch   TensorFlow   HuggingFace   LangChain   Scikit-learn   Pandas   NumPy   React   Node.js   Express.js   MongoDB   Postgres   AWS   Docker   Git  


✨ Highlighted Projects

Here are some projects I'm particularly proud of. (Note: Keeping only the specified projects)

LLMThinkBench
An Advanced Reasoning and Overthinking Evaluation Framework for Language Models
SLMs reasoning Leaderboard
Towards Reasoning Ability of Small Language Models
Datasense
An Intelligent Data Visualization and Story Generator
ai verifica DocOnLine Social Distancing Alert

You can explore more of my work in my repositories tab!


📊 GitHub Stats & Activity


📫 Get In Touch

Thanks for stopping by! ✨

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors