Skip to content
View aghasalim's full-sized avatar
4 followers · 2 following

Achievements

Achievement: Quickdraw

Achievements

Achievement: Quickdraw

Block or report aghasalim

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.

Content in all repositories owned by your account will be closed.
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
aghasalim/README.md

Aghasalim Mustafazada

Third year AI student at Howest, Belgium. Mostly anomaly detection and interpretability. I get suspicious of results that only work on the benchmark, so I check my own numbers before anyone else does.

Open to AI and backend internships.

Tools

Python, C++, SQL, Bash. PyTorch, scikit-learn, LightGBM, Transformers, SHAP. FastAPI, Streamlit, Docker, GitHub Actions, PostgreSQL, Raspberry Pi, Arduino.

Other

Gold medal at the International STEM Olympiad in mathematics, 2022. Scored 0.9086 on the IEEE-CIS private leaderboard, which Kaggle graded against labels I never got to see.

Contact

salim.mustafazada@student.howest.be

Website · LinkedIn · Kaggle · ORCID

Pinned Loading

  1. arc-prize-2026 arc-prize-2026 Public

    ARC-AGI-2 attempt: object-centric DSL with a verifier-backed program search. 3.9% on public training, 0% on public evaluation -- and a characterisation of why.

    Python 2

  2. eu-ai-act-rag eu-ai-act-rag Public

    Grounded QA over the EU AI Act where the evaluation harness is the deliverable: retrieval, faithfulness and hallucination metrics over 45 hand-written questions

    Python 2

  3. explainable-defect-detector explainable-defect-detector Public

    Anomaly detection for visual defect inspection: trained on normal images only, with localisation. PyTorch + MVTec AD.

    Python 2

  4. lora-forgetting lora-forgetting Public

    LoRA fine-tuning a small LLM for structured extraction, with the catastrophic-forgetting check most projects skip. Both numbers reported.

    Python 2

  5. mlops-fraud-pipeline mlops-fraud-pipeline Public

    Fraud model behind FastAPI, CI gating and drift monitoring -- where the monitoring is measured against a healthy null, not just demoed against an injected failure.

    Python 2

  6. ieee-fraud-ml ieee-fraud-ml Public

    Working IEEE-CIS Fraud Detection end to end, where the documented decision trail is the deliverable, not the leaderboard score.

    Python 2