Skip to content
View AnuruddhaPaul's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report AnuruddhaPaul

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
ANURUDDHAPAUL/README.md

👋 Hi, I'm ANURUDDHA PAUL

Typing SVG

🎓 About Me

class AIResearcher:
    def __init__(self):
        self.name = "Anuruddha Paul"
        self.role = "Computer Science Student & AI Researcher"
        self.institution = "KIIT University"
        self.cgpa = 9.8
        self.location = "India 🇮🇳"
        self.research_interests = [
            "Computer Vision",
            "Deep Learning",
            "Vision Transformers",
            "Object Detection (YOLO)",
            "Edge AI & IoT",
            "Large Language Models"
        ]
        
    def say_hi(self):
        print("Thanks for visiting! Let's innovate together in AI! 🚀")

me = AIResearcher()
me.say_hi()

🔬 Research Focus

Specializing in Computer Vision, Deep Learning, and AI Systems Development

I'm a passionate Computer Science student at KIIT University with a strong focus on cutting-edge AI research. My work spans hybrid neural architectures (combining Vision Transformers with YOLO), edge deployment on resource-constrained devices, and building production-grade AI applications. Currently maintaining a 9.8+ CGPA while actively contributing to research in computer vision and machine learning.


🚀 Current Projects

🎯 YOLO HARVEST

Advanced object detection system combining YOLO architecture with transformer-based attention mechanisms for agricultural applications.

Tech Stack:

  • PyTorch, YOLOv8
  • Vision Transformers
  • CUDA optimization
  • Edge deployment

🤖 AI Research Paper Generator

Agentic AI system using LangGraph and Google Gemini to automatically generate research papers from arXiv papers.

Tech Stack:

  • LangGraph, LangChain
  • Google Gemini 2.0/2.5
  • Streamlit, LaTeX
  • arXiv API

💬 Multi-Model QA System

Ensemble LLM system using Groq API for question answering with multiple reasoning models.

Tech Stack:

  • Groq API (Llama 3.1, Qwen)
  • Vision-Language Models
  • FastAPI, Python
  • Ensemble reasoning

🌐 NOVA AI Assistant

Multimodal AI assistant with real-time vision, voice interaction, and intelligent conversation capabilities.

Tech Stack:

  • Google Gemini
  • ElevenLabs, Whisper
  • Streamlit, OpenCV
  • IP Webcam integration

💻 Tech Stack

Programming Languages

Python Java JavaScript SQL

Machine Learning & AI

PyTorch TensorFlow Scikit Learn OpenCV Keras Hugging Face

AI Frameworks & Tools

LangChain LangGraph CUDA ONNX

Web Development & APIs

FastAPI Streamlit Flask Node.js React

Databases & Cloud

MongoDB PostgreSQL MySQL Google Cloud AWS

Development Tools

Git Docker VS Code Jupyter Linux LaTeX

Hardware & Edge AI

Raspberry Pi NVIDIA


📊 GitHub Statistics

💻 Most Used Languages


🏆 GitHub Trophies

trophy


🔬 Research & Publications

📝 Research Areas

Area Focus Status
Computer Vision Vision Transformers, Hybrid Architectures (CNN+ViT) 🔬 Active Research
Object Detection YOLO-based systems, Real-time detection 🚀 Production
Edge AI Raspberry Pi deployment, Model optimization ⚡ Ongoing
LLM Systems Multi-model ensembles, Reasoning evaluation 💡 Experimental
Vision-Language Models Multimodal understanding, VQA systems 📚 Learning
📄 Research Papers & Projects

In Progress

  • Hybrid YOLO-Transformer Architecture for Agricultural Object Detection

    • Combining YOLO efficiency with Transformer attention mechanisms
    • Focus on HARVEST dataset and real-world deployment
  • Multi-Model LLM Evaluation Framework

    • Comparative analysis of reasoning capabilities across models
    • Using Groq API for efficient inference

Completed Projects

  • Wildlife Classification with Cross-Dataset Validation

    • Deployed on edge devices (Raspberry Pi)
    • 100+ GB dataset processing
  • AlexNet & CNN Architectures from Scratch

    • Educational implementations in TensorFlow/Keras
    • Complete mathematical derivations

💼 Professional Experience

%%{init: {'theme':'dark'}}%%
timeline
    title My AI/ML Journey
    2023 : Started Deep Learning
         : Built first CNN models
    2024 : Advanced Computer Vision
         : YOLO & Vision Transformers
         : Research Paper Contributions
    2025 : Production AI Systems
         : Edge AI Deployment
         : LLM & Agentic AI
         : 9.8+ CGPA Achievement
Loading

🎯 2025 Goals

  • [✅] 🎓 Maintain 9.8+ CGPA at KIIT University
  • [✅] 📝 Publish research paper on Hybrid YOLO-Transformer Architecture
  • [✅] 🚀 Deploy 3+ production-grade AI applications
  • 🌟 Contribute to major open-source AI projects
  • 🏆 Win competitive programming competitions
  • 💻 Master LangGraph & Agentic AI systems
  • [✅] 📊 Build comprehensive ML portfolio with 20+ projects
  • [✅] 🤝 Collaborate with AI research labs

💡 Skills & Expertise

🧠 Machine Learning & Deep Learning

Core Competencies:

  • Neural Network Architectures (CNNs, RNNs, Transformers)
  • Vision Transformers (ViT, Swin Transformer, DEIT)
  • Object Detection (YOLO, Faster R-CNN, SSD)
  • Model Training & Optimization
  • Transfer Learning & Fine-tuning
  • Data Augmentation & Preprocessing
  • Model Evaluation & Ablation Studies

Advanced Topics:

  • Hybrid Architectures (CNN+ViT, CNN+RNN)
  • Attention Mechanisms
  • Model Compression & Quantization
  • Edge AI & Mobile Deployment
  • Cross-Dataset Validation
🔍 Computer Vision

Techniques:

  • Image Classification
  • Object Detection & Tracking
  • Semantic Segmentation
  • Instance Segmentation
  • Pose Estimation
  • Image Enhancement
  • Video Analysis

Tools & Libraries:

  • OpenCV, PIL/Pillow
  • Albumentations
  • YOLO (v5, v8)
  • MMDetection
  • Detectron2
🤖 Large Language Models & AI Agents

Frameworks:

  • LangChain & LangGraph
  • Hugging Face Transformers
  • OpenAI API, Groq API
  • Google Gemini

Applications:

  • Agentic AI Systems
  • RAG (Retrieval Augmented Generation)
  • Multi-Model Ensembles
  • Vision-Language Models
  • Tool-using Agents
⚡ Edge AI & IoT

Platforms:

  • Raspberry Pi (4/5)
  • NVIDIA Jetson
  • Google Coral

Technologies:

  • TensorFlow Lite
  • ONNX Runtime
  • Model Optimization
  • Real-time Inference
💻 Software Engineering

Full Stack Development:

  • Frontend: React, HTML/CSS/JS
  • Backend: FastAPI, Flask, Node.js
  • Databases: MongoDB, PostgreSQL, MySQL
  • Cloud: Google Cloud, AWS
  • DevOps: Docker, Git, CI/CD

Best Practices:

  • Clean Code & Design Patterns
  • API Design & RESTful services
  • Testing & Debugging
  • Documentation

💬 Let's Collaborate!

I'm always open to:

  • 🔬 Research collaborations in AI/ML
  • 💼 Interesting project opportunities
  • 🎓 Academic discussions
  • 🤝 Open-source contributions
  • 📚 Knowledge sharing

Feel free to reach out! ✉️


📚 Latest Blog Posts

  • 🔥 Building Production-Grade AI Agents with LangGraph
  • 🎯 YOLO vs Vision Transformers: A Comprehensive Comparison
  • ⚡ Deploying ML Models on Raspberry Pi: A Complete Guide
  • 🤖 Multi-Model LLM Ensembles: Theory and Practice
  • 🌟 From Research to Production: My AI Journey

🎓 Education

🏛️ KIIT University

Bachelor of Technology in Computer Science | 2023 - 2027
CGPA: 9.8+ | Top Performer

Relevant Coursework:

  • Machine Learning & Deep Learning
  • Computer Vision
  • Data Structures & Algorithms
  • Database Management Systems
  • Operating Systems
  • Computer Networks
  • Cloud Computing

Achievements:

  • 🏆 Consistent Dean's List awardee
  • 🌟 Top 5% in Computer Science program
  • 📝 Research paper contributions
  • 💻 Multiple hackathon participations

💭 Random Dev Quote


⚡ Fun Facts

const aboutMe = {
    code: ["Python", "Java", "C++", "JavaScript"],
    askMeAbout: ["AI", "ML", "Computer Vision", "Deep Learning", "Edge AI"],
    technologies: {
        frameworks: ["PyTorch", "TensorFlow", "LangChain"],
        tools: ["Docker", "Git", "CUDA"],
        cloud: ["Google Cloud", "AWS"]
    },
    currentFocus: "Building Agentic AI Systems",
    funFact: "I debug with print statements and I'm proud of it! 🐛"
};


Show some ❤️ by starring some of my repositories!

© 2025 ANURUDDHA PAUL. All rights reserved.

Pinned Loading

  1. Alex-Net-from-scratch Alex-Net-from-scratch Public

    Jupyter Notebook

  2. Neural-Network-from-scratch Neural-Network-from-scratch Public

    Jupyter Notebook 1

  3. ai-researcher-main ai-researcher-main Public

    Python

  4. ai-therapist-2.0-main ai-therapist-2.0-main Public

    Python

  5. MCP_SERVER MCP_SERVER Public

    Python