Skip to content
View ShahwarYasir's full-sized avatar

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report ShahwarYasir

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. 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
ShahwarYasir/README.md 
██████╗ ██╗   ██╗██████╗       ███████╗    ███████╗██╗  ██╗ █████╗ ██╗  ██╗██╗    ██╗ █████╗ ██████╗
██╔══██╗██║   ██║██╔══██╗      ██╔════╝    ██╔════╝██║  ██║██╔══██╗██║  ██║██║    ██║██╔══██╗██╔══██╗
██║  ██║██║   ██║██████╔╝█████╗█████╗      ███████╗███████║███████║███████║██║ █╗ ██║███████║██████╔╝
██║  ██║██║   ██║██╔══██╗╚════╝██╔══╝      ╚════██║██╔══██║██╔══██║██╔══██║██║███╗██║██╔══██║██╔══██╗
██████╔╝╚██████╔╝██║  ██║      ███████╗    ███████║██║  ██║██║  ██║██║  ██║╚███╔███╔╝██║  ██║██║  ██║
╚═════╝  ╚═════╝ ╚═╝  ╚═╝      ╚══════╝    ╚══════╝╚═╝  ╚═╝╚═╝  ╚═╝╚═╝  ╚═╝ ╚══╝╚══╝ ╚═╝  ╚═╝╚═╝  ╚═╝

Typing SVG

LinkedIn Gmail Kaggle

Who I Am

Hi, I'm Dur-e-Shahwar, a third-year BS Artificial Intelligence student at COMSATS University Islamabad. I like turning ideas into working systems, especially in computer vision, multimodal AI, and agentic workflows. Cybersecurity is my secondary academic interest.

What I'm Working On

  • Recreating research papers from scratch to understand them properly (starting with LLM and agentic papers)
  • Building agentic AI projects with LangGraph and FastAPI
  • Looking for research opportunities and summer internships

Featured Projects

Project What it does Stack
Multimodal VQA System Answers questions about images with BLIP-VQA and a ViLT fallback, reaching 93.8% accuracy PyTorch, Hugging Face, Gradio
Helmet & License Plate Detection Real-time detection of helmets and number plates YOLOv8, OpenCV
Patient Triage Agent Agentic workflow that helps prioritize patients LangGraph, FastAPI, ChromaDB
Study Abroad Assistant Team project that guides students through study abroad decisions LangGraph, FastAPI
Attention Is All You Need Paper reimplementation of the Transformer PyTorch
Crop Yield Prediction Regression model with R² = 0.97 Python, scikit-learn

Tech Stack

Python PyTorch FastAPI Hugging Face LangGraph OpenCV Git

GitHub Stats

Followers Repos Profile Views

Certifications

  • NCAI Agentic AI Bootcamp

Let's Connect

Open to collaborations, research projects, and internships. Reach out on LinkedIn or by email.

Pinned Loading

  1. transformer-from-scratch transformer-from-scratch Public

    A from-scratch PyTorch reimplementation of the Transformer architecture from Vaswani et al., 2017 ("Attention Is All You Need"), trained on Multi30k (German → English translation), with every compo…

    Python

  2. hasana157/patient-triage-agent hasana157/patient-triage-agent Public

    Agentic AI-powered emergency triage decision-support system with contradiction detection, action-chain planning, failure recovery, and operational outcome simulation.

    Dart 1

  3. image-insight-VQA image-insight-VQA Public

    Forked from hasana157/image-insight-VQA

    A multimodal Visual Question Answering system that answers natural-language questions about images using BLIP and Hugging Face Transformers.

    Jupyter Notebook

  4. GDGOC-PIEAS-AI-ML-HACKATHON GDGOC-PIEAS-AI-ML-HACKATHON Public

    Forked from ZayanRashid295/GDGOC-PIEAS-AI-ML-HACKATHON

    Jupyter Notebook

  5. Study-Abraod-Assistant-SAA- Study-Abraod-Assistant-SAA- Public

    Study Abroad Assistant is a full-stack academic demo project that helps students plan international education applications. It includes a React student portal, a React admin portal, and a simple fr…

    JavaScript 1

  6. crop-yield-prediction crop-yield-prediction Public

    Machine learning pipeline for predicting global crop yields using FAO data (1961–2016). Implements Linear Regression, Random Forest, and ANN, achieving R² = 0.97 with an optimized Random Forest model.

    Jupyter Notebook