Skip to content

Navigation Menu

Sign in
Sign up
@sepehrkdi
sepehrkdi
Follow

Sepehr Khodadadi sepehrkdi

Computer Science Student @UniGe

Highlights

  • Pro

Block or report sepehrkdi

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
sepehrkdi /README.md

Sepehr Khodadadi

M.Sc. student in Data Science and Engineering (AI track) at the University of Genoa, working on machine unlearning and trustworthy machine learning at MaLGa, in collaboration with Télécom Paris.

🌐 Homepage: sepehrkdi.github.io · 🎓 Google Scholar · 💼 LinkedIn

Highlights

  • 📄 trail: reproducible machine-unlearning evaluation library; our paper TRAIL: Navigating the Jungle of Machine Unlearning Evaluation is accepted as an oral presentation at the ECCV 2026 Workshop and Challenge on Unlearning and Model Editing (U&ME).
  • 🩻 multi-agent-clinical-decision-support: BDI multi-agent system with chest X-ray imaging agents and report-text NLP agents under a Prolog consensus mechanism (University of Genoa course project).
  • 🩺 retinal-vessel-segmentation-alog: training-free, interpretable-by-design classical pipeline (DRIVE), paired with an Attention U-Net counterpart.
  • 🗿 3d-geological-modeling: rock-mass slicing, block extraction, and volumetric analysis.
  • 📊 MediaBiasVisualization: D3.js scrollytelling on global conflicts and media attention (live demo).

Pinned Loading

  1. 3d-geological-modeling 3d-geological-modeling Public

    3D geological modeling toolkit: rock-mass slicing, block extraction, volumetric analysis (Trimesh/Open3D)

    Jupyter Notebook 4

  2. retinal-vessel-segmentation-attention-unet retinal-vessel-segmentation-attention-unet Public

    Attention U-Net for retinal vessel segmentation with hybrid Dice+Focal loss and dense patch augmentation

    Jupyter Notebook 2

  3. MediaBiasVisualization MediaBiasVisualization Public

    Shifting Spotlights: D3.js scrollytelling on global conflicts and media attention (UCDP data)

    Jupyter Notebook 1

  4. ar-gallery-presenter ar-gallery-presenter Public

    Ground-anchored AR presenter for wall-mounted paintings (Unity, Vuforia, ARCore)

    C#

  5. retinal-vessel-segmentation-alog retinal-vessel-segmentation-alog Public

    ALoG: training-free, interpretable-by-design classical pipeline for retinal vessel segmentation (DRIVE)

    Jupyter Notebook

AltStyle によって変換されたページ (->オリジナル) /