Skip to content
View MENT0Z's full-sized avatar
🎯
Focusing
🎯
Focusing
8 followers · 7 following

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report MENT0Z

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 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
ment0z/README.md

Hi 👋, It's me MRU (Madan Raj Upadhyay)

🧠 About Me

I’m a research-oriented developer exploring Artificial Intelligence, Machine Learning, and LLM systems with a strong focus on practical, real-world deployment.

My work lies at the intersection of:

  • 🔬 AI Research & Experimentation
  • ⚙️ Efficient model design (small models, CPU-friendly)
  • 📱 AI-powered applications (Android + Edge AI)
  • 🗄️ Backend & Data Handling

I enjoy breaking systems, fixing flaws, and building better solutions through research-driven development.

🔬 Research Interests

  • 🤖 Large Language Models (LLMs)
  • 🧠 Model Compression & Fine-Tuning
  • 📉 Low-resource & CPU-based AI
  • 🔍 AI for Business Automation
  • 📊 Data Analysis & Pattern Mining
  • 🧪 Experimental AI Prototypes

🛠️ Tech Stack

Languages & Core:
Python C++ Kotlin Java

AI / ML:
PyTorch TensorFlow Scikit-Learn HuggingFace ONNX

Systems & Tools:
Android SDK SQL Firebase Linux Git SpringBoot

🧪 Research & AI Projects

🔹 LLM Optimization Experiments

  • Fine-tuning small language models for task-specific reasoning
  • CPU-only inference & latency reduction
  • Prompt-engineering vs fine-tuning comparisons

🔹 AI-Powered Business Systems

  • Inventory & billing systems enhanced with AI insights
  • Offline-first AI decision support
  • Data-driven automation tools

🔹 Experimental Prototypes

  • Lightweight AI agents
  • Domain-specific mini-models
  • AI + Mobile hybrid applications

👉 Most projects are experimental, iterative, and research-driven.

📊 GitHub Analytics

🧬 Research Mindset

“Build → Measure → Break → Improve”
I treat every project as an experiment, prioritizing:

  • Reproducibility
  • Performance metrics
  • Real-world constraints

🌐 Connect & Collaborate

  • 🤝 Open to AI research collaboration
  • 📧 Email: your email
  • 💼 LinkedIn: your LinkedIn

⭐ If my work interests you, feel free to explore or collaborate.

Pinned Loading

  1. MindMaster MindMaster Public

    MindMaster is your virtual study environment which will provide dynamic content delivery with respect to your emotion.

    JavaScript 1

  2. Vehicle-Cut-in-Detection Vehicle-Cut-in-Detection Public

    This project utilizes the YOLO (You Only Look Once) object detection model and SORT (Simple Online and Realtime Tracking) to detect and track vehicles in a video stream to detect the vehicle sudden…

    Jupyter Notebook 2

  3. IMS IMS Public

    IMS is a complete, offline-first Inventory Management System Android application designed for retailers, wholesalers, and small-to-medium businesses. It manages stock, purchases, sales, customers, …

    Kotlin 1

  4. Visitor-Management-System- Visitor-Management-System- Public

    This backend powers the Visitor Management System, providing secure authentication, visitor approvals, and real-time tracking. Built with Spring Boot, it follows Microservices Architecture with API…

    Java

  5. Smart-Pothole-Detection-ML Smart-Pothole-Detection-ML Public

    This project is OpenVINO integrated AIOT project which detects Pothole by photo,liveCam,videos

  6. Subject-Segmentation-Android-App Subject-Segmentation-Android-App Public

    This project demonstrates an efficient image subject segmentation Android application built with Jetpack Compose.

    Kotlin 1