Skip to content
View raslenabb12's full-sized avatar
0 followers · 1 following

Highlights

  • Pro

Block or report raslenabb12

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
raslenabb12/README.md

Hi, I'm Raslen 👋

Computer Science Undergrad | Edge AI & Applied Machine Learning

I am a Computer Science student based in Tunisia, graduating in late 2027. My passion lies in Applied Artificial Intelligence, Edge Computing (On-Device ML), and Natural Language Processing.

I specialize in bridging the gap between heavy deep learning models and mobile architectures—optimizing AI to run efficiently, locally, and privately on edge devices.

Research Interests

  • Edge AI & Mobile Computing: Deploying LLMs and Vision models on resource-constrained devices (Android).
  • Applied NLP: Fine-tuning large language models for domain-specific tasks and low-resource languages (English-to-Arabic).
  • Privacy-Preserving AI: Architecting systems that process sensitive data (like photos or browsing history) entirely on-device.

Featured Projects & Applied Research

Memoria: On-Device Vision-Language Image Retrieval

A privacy-first Android application that allows users to search their local photo gallery using natural language queries.

  • Architecture: Extracts image and text embeddings locally on the device without relying on cloud APIs.
  • Tech Stack: Kotlin, Android SDK, On-Device AI/Vision Models.
  • Challenge Solved: Optimized vector search and memory management to run complex embedding models smoothly on a mobile CPU/NPU.

YBrowser-Ai: Edge-AI Powered Web Browser

An experimental Android web browser integrating local machine learning for real-time content processing.

  • Architecture: Implements on-device ML models for intelligent content filtering and enhanced browsing privacy.
  • Tech Stack: Kotlin, Android WebView, Local ML inference.

Manhwa-NLLB-1.3B-EnAr-v2: Domain-Specific NLP Translation (Link to your HF/Repo)

Fine-tuned a 1.3 Billion parameter Meta NLLB model for specialized English-to-Arabic translation.

  • Process: Curated a custom dataset of Manhwa (comic) dialogues, handled data preprocessing, and optimized training pipelines.
  • Tech Stack: Python, PyTorch, Hugging Face Transformers, LoRA/QLoRA (if applicable).

Technical Arsenal

  • AI & Machine Learning: PyTorch, Hugging Face, TensorFlow Lite, NLP, Vision-Language Models (VLMs).
  • Mobile & Edge Computing: Android OS, Kotlin, Java, Mobile Model Quantization.
  • Backend & Data: Python, SQL, REST APIs, Git/GitHub.

📈 GitHub Stats

Raslen's GitHub Stats

📫 Let's Connect

Looking to collaborate on Edge AI research or discuss graduate opportunities!

Popular repositories Loading

  1. Tanuki Tanuki Public

    A modern, high-performance Android manga tracker and explorer powered by AniList and MyAnimeList.

    Kotlin 2

  2. AnimeDrop AnimeDrop Public

    Live Anime Countdown RecyclerView Adapter This feature powers a RecyclerView that displays anime items with a live countdown timer showing how many days, hours, minutes, and seconds are left until …

    Kotlin 1

  3. Manhwa-NLLB-1.3B-EnAr-v2 Manhwa-NLLB-1.3B-EnAr-v2 Public

    This is a fine-tuned translation model based on facebook/nllb-200-distilled-600M. It is specifically trained to translate Manhwa, Manga, and Webnovels from English to Arabic.

    Jupyter Notebook 1

  4. YBrowser-Ai YBrowser-Ai Public

    YBrowser is an experimental Android web browser that ditches traditional static blocklists (like EasyList) in favor of a local, on-device Artificial Intelligence.

    Kotlin 1 1

  5. Memoria Memoria Public

    Memoria is an open-source Android app that lets you search your photo gallery using natural language — type "dog at the beach", "birthday cake", or "snowy mountains" and it finds the right photos i…

    Kotlin 1

  6. raslenabb12 raslenabb12 Public