Skip to content
View Nauman-Irshad's full-sized avatar

Block or report Nauman-Irshad

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
Nauman-Irshad/README.md

Hi 👋, I'm Nauman Irshad Ali Shah

🤖 AI Researcher | Mini-LLMs | Conversational AI | Flutter Developer

profile views


🧠 About Me

As an AI researcher and Flutter developer, I have strong hands-on experience in Mini-LLMs, conversational AI, machine learning, computer vision, and mobile application development. I am a co-author of a research publication on "Comparative Analysis of OpenPose COCO and MPI Models for Depth Estimation from 2D Human Images", highlighting my work in computer vision and 3D human pose estimation, with a strong focus on publication-oriented and applied research.

As a researcher and developer, I am currently working on advanced AI systems including 3D avatar generation using PIFuHD for metaverse applications, AI-based virtual try-on systems, secure medical NLP chatbots, and an AI assistant powered by Mini-LLM architectures such as sentence-transformers/all-MiniLM-L6-v2.

As a Flutter developer at A&N Creation, I build cross-platform mobile applications and integrate AI-driven features with backend systems, using Python, Java, JavaScript, Dart, Flutter, React.js, HTML, and CSS in real-world development environments.

As an innovator and content creator, I founded Fluent AI, an AI-powered English learning platform using voice agents to improve grammar and pronunciation. I have also achieved over 1 million views on YouTube, reflecting strong communication, leadership, and community engagement skills.


💼 Projects

  • Jovix: An innovative e-commerce platform connecting buyers and sellers globally, featuring global marketplace, dynamic vouchers, diverse categories, secure authentication, audio introduction, admin user profile, real-time notifications, and a Gemini-powered live chatbot. Developed in collaboration with Abdullah Habib.
  • 3D Avatar Generation (PIFuHD): Creating 3D avatars for Metaverse applications using PIFuHD and advanced computer vision techniques.
  • Virtual Try-On Systems: AI-based systems for apparel and accessory visualization in real time.
  • Secure Medical NLP Chatbot: AI-powered chatbot for medical guidance and secure communication.
  • AI Assistant using Mini-LLMs: Conversational AI assistant leveraging sentence-transformers/all-MiniLM-L6-v2.
  • AI-Integrated Security Measures: Systems incorporating AI for enhanced cybersecurity and anomaly detection.
  • NLP Project: GPT-2 Fine-Tuning: Fine-tuned GPT-2 on a 120k-song corpus for song prediction and generation.
  • Python Projects: Audio MIDI Editor/Generator.
  • GoLang Projects: Image Color Picker Tool.
  • JavaScript Projects: JS Animator.

🔬 Research Interests

  • Artificial Intelligence & Machine Learning
  • Mini Large Language Models (Mini-LLMs)
  • Computer Vision & 3D Reconstruction
  • Natural Language Processing
  • Conversational AI & Secure AI Systems

🛠 Tech Stack

Image Image Image Image Image

Image Image Image Image

Image Image Image Image


📌 Current Focus

  • Research Publications in AI & ML
  • 3D Avatars & Virtual Try-On Systems
  • Conversational AI & Voice Agents
  • AI-Integrated Mobile Applications

🤝 Let’s Collaborate I’m open to research collaboration, AI product development, and publication-oriented projects in AI, Machine Learning, Computer Vision, NLP, and Cybersecurity. I am also seeking guidance and direction to grow further in the AI and Machine Learning fields.

Pinned Loading

  1. Spotify-Song-Popularity-Prediction- Spotify-Song-Popularity-Prediction- Public

    Jupyter Notebook 1

  2. train-and-Finetune-Gpt-2-LSTM-on-self-60k-dataset train-and-Finetune-Gpt-2-LSTM-on-self-60k-dataset Public

    Jupyter Notebook 1

  3. backend_deployment_upload_vercel_api_testing backend_deployment_upload_vercel_api_testing Public

    Python

  4. cached_lm_GPT2Tokenizer_64_gpt2_train_corpus cached_lm_GPT2Tokenizer_64_gpt2_train_corpus Public

    Jupyter Notebook

  5. Compiler-Construction-P-2-bison-error-handlingubuntusyntax-lexer-parser-SDD-SDT-3AC-DAG-First-follow Compiler-Construction-P-2-bison-error-handlingubuntusyntax-lexer-parser-SDD-SDT-3AC-DAG-First-follow Public

    C

  6. gpt2_finetuned gpt2_finetuned Public