🎓 Pursuing a Master's Degree in Computer Science at the University of Trento, Italy. 🇮🇹 Bachelor’s Degree in Statistics from Hacettepe University, Turkey. 🇹🇷

🔍As part of my MSc thesis, I am developing unsupervised, generator-agnostic algorithms for detecting generated or altered media by extracting high-level semantic features, contributing to an EU-funded multimedia forensics project. 🕵️‍♂🇪🇺

💡 Interested in Medical AI and NeuroAI applications, leveraging multi-modal fusion techniques like contrastive learning to advance system-level insights in healthcare and neuroscience and like to ask questions. 🧠

🌿 I like to think and try new ideas. & When away from the computer, I enjoy literature📚, ice skating❄️, and spending time outdoors.

  

Here are some of the exciting projects I’ve been working on:

• Test-Time Domain Adaptation: Reimplementation of "MEMO: Test Time Robustness via Adaptation and Augmentation. Applied to the ImageNet-A dataset to handle domain shifts in image classification.
• Multimodal RAG: Designed a secure and CPU-efficient retrieval-augmented generation system for genetic research. The paper is set to be submitted as a preprint shortly.
• DeepFake Detection: A non-linear classifier using CLIP features and a non-linear classifier for detecting AI-generated multimedia.
• Local Sequence Alignment: Implemented the Smith-Waterman Algorithm for local sequence alignment in bioinformatics.
• Metagenomic Analysis: Characterized the oral microbiome using uSGB analysis.
• Knowledge Graph Engineering: Developed a knowledge graph to map Trentino Healthcare Facilities for improved accessibility.
• Interactive Model Inspection for Multi-Class Multi-Label Language Models: Using Plotly, t-sne method, and embeddings to detect any issues (will add the code).

Machine Learning/AI Tools

Programming Languages

Development Tools

Cloud and DevOps Tools

Design Tools

Foster Insight: Founder & CEO (2019 - 2022) 🏢

• Led the development of Turkish NLP solutions for the banking industry, including ontologies and domain-specific resources for language models.
• Managed a team to deliver NLP services and APIs to enhance customer interactions, automate document processing, and streamline document reviewing using advanced NLP algorithms.
• Secured TÜBİTAK BIGG 1512 R&D Fund (2020-2021)
  TRL 4-5

Philip Morris International: Global Data & Analytics Lead (Jun 2022 - Mar 2023) 🌍

• Coordinated the rollout of AI projects in compliance with global company standards, focusing on predictive maintenance at the factory as a subject matter expert TRL 8-9

Wonderflow: Curricular ML/NLP Intern (Aug 2023 - Feb 2024) 🤖

• Trained multi-class transformer models in Turkish and developed a QA pipeline to transform sentence transformers into segmented models using OpenAI.
• Created an interactive model inspection tool for linguists TRL 7-8

TrueBees: (Thesis) Research Intern (Aug 2024 - ongoing) 🔬

• Working on my MSc thesis, focusing on multimedia forensics TRL 3-4

^{*Technology Readiness Levels (TRL) are a method for estimating the maturity of technologies during the acquisition phase of a program. The scale ranges from 1 to 9, with 9 being the most mature technology. For more information, refer to the European Commission's TRL guidelines.}

Feel free to reach out if you're looking for a research collaborator—I enjoy engaging in discussions and am open to volunteering on ideas that have the potential to make a meaningful impact. 🌱

• Email: [email protected]
• Linkedin: Zehra Korkusuz