Skip to content
View devansh2506's full-sized avatar

Block or report devansh2506

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
devansh2506/README.md

Hi, I'm Devansh Kedia

💫 About Me

I’m a third-year B.Tech student at Delhi Technological University (DTU), actively building my skills in Artificial Intelligence and Machine Learning. I enjoy working at the intersection of theory and practice, turning ideas into functional, real-world systems.

I learn best by experimenting and building—constantly exploring new concepts, reading research, and implementing models from scratch. I’m particularly interested in understanding why things work, not just how to use them.

Driven by curiosity and a growth mindset, I’m always looking to deepen my understanding and improve through hands-on work.


💻 Tech Stack

Python C++ NumPy Pandas SciPy Statsmodels Matplotlib Seaborn Jupyter scikit-learn XGBoost LightGBM MLflow PyTorch TensorFlow Keras Transformers Hugging Face LangChain OpenAI Weights & Biases OpenCV FastAPI Postman Postgres Docker Google Cloud RunPod Git GitHub Linux Telegram


snake gif

Pinned Loading

  1. JARVIS-A-Multi-Agentic-Personal-Assistant JARVIS-A-Multi-Agentic-Personal-Assistant Public

    JARVIS is an advanced Multi-Agent AI System built using LangGraph and powered by Google's Gemini 2.5 Flash models.

    Python 1

  2. Multi-Agentic-Deep-Research-System Multi-Agentic-Deep-Research-System Public

    A sophisticated, asynchronous multi-agent AI system built with LangGraph, LangChain, and Tavily Search to autonomously scope, research, and synthesize comprehensive reports on any topic.

    Python

  3. Virtual-Try-On Virtual-Try-On Public

    This project presents an end-to-end AI-driven platform for immersive virtual try-on experiences. Users can preview garments on their own images, discovering how clothing items fit and look in a rea…

    Jupyter Notebook

  4. Crowd_Count_Estimator Crowd_Count_Estimator Public

    Crowd counting – estimating the number of people in an image – is a key task in computer vision with applications in public safety, surveillance, and event management.

    Jupyter Notebook