Skip to content
View hassen8's full-sized avatar
5 followers · 17 following

Block or report hassen8

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
hassen8/README.md

Typing SVG


MSc in AI from Uni. Bologna. Previously ML-Research intern at Datalogic in Eugene, Oregon. Worked on edge AI designing an embedding based classifier for an end-to-end produce recognition pipeline, using von-Mises distributions as Mixtures for modeling data that lies on a hypersphere. Improved on previous GMM based classifier by 5% Top-4 Recall.


📍 Bologna, Italy

LinkedIn Kaggle Gmail


Projects

Project What
🔭 AstraGraph GraphRAG for codebases — Neo4j + Qdrant + LangGraph · live demo
🏥 Matryoshka-ICD Automated ICD coding from radiology reports with nested embeddings
⚖️ Emotion Bias Audit Fairness audit of emotion AI against neurodiverse individuals
🌊 Clouded SST U-Net reconstructing cloud-occluded sea surface temperature · 0.48 RMSE
📅 Sports Scheduling Same problem, four solvers: CP · MIP · SMT · SAT

Interests

Graph-RAG   Low-resource Languages   Multimodal AI   ViT   Manifold Geometry


Looking for AI/ML Research or Engineering roles, where the gap between the theory and the applied ML is the problem to solve. Open to anything accross representation learning, multimodal systems, LLM-related , agentic and rag systems.


Stack

Python PyTorch TensorFlow Keras scikit-learn NumPy Pandas HuggingFace LangChain LangGraph OpenCV Docker MLflow W&B MongoDB Neo4j Qdrant Git Linux C++ Java JavaScript


Stats

Stats


Publications

📄 Amharic ATS: Graph-Based vs. Statistical Extractive Summarization · IEEE Xplore 2023
📄 Automatic Extractive Text Summarization for Ho Language · IEEE Xplore 2023

Quote

quote

Pinned Loading

  1. astragraph astragraph Public

    GraphRAG system that ingests codebases into Neo4j + Qdrant for natural-language querying via hybrid (structural and semantic) retrieval

    Python

  2. sports_tournament_scheduling sports_tournament_scheduling Public

    Sports Tournament scheduling solved via CP, MIP, SMT, and SAT with MiniZinc and Python , fully containerized with automated solution checker

    Python 2

  3. Matryoshka-ICD Matryoshka-ICD Public

    Automated ICD coding system based on PLM-ICD, using Matryoshka Representation Learning (MRL) and Label Aware Attention to predict ICD codes based on text reports.

    Python

  4. emotion_recognition_bias_auditing emotion_recognition_bias_auditing Public

    Fairness audit of emotion recognition AI against neurodiverse individuals using Grad-CAM, LIME, and occlusion sensitivity, grounded in EU Trustworthy AI guidelines

    Jupyter Notebook