| FazBrowse GitHub Viewer | Trending | | Home |
| Tools: [Original HTTPS Page] |
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.
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abuseData scientist & NLP researcher · Warsaw
Explainable multimodal LLMs · applied ML · open-source research tooling
I study Data Science (MSc) at Warsaw University of Technology — BSc with honors. I care about making multimodal LLMs explainable and turning research into tools people can actually install and reuse.
Most of my recent work sits at the intersection of NLP, Shapley-value XAI, and practical data science. I previously built Botuj (AI chat + voice); I’m no longer actively developing it.
Roles & experience → LinkedIn
| Project | What it is | |
|---|---|---|
| Flagship | nlp-shap · docs · PyPI | Shapley-style explainability library for NLP / multimodal LLM pipelines |
| Tools | lm-studio-dash | Dashboard for local LM Studio usage, hardware, and chat analytics |
| Tools | AutoPrep · PyPI | AutoML preprocessing, explainability, and LaTeX reporting |
| Archive | MLLM-Shap | Thesis / ACL predecessor of nlp-shap |
| Coursework | Galaxy-Images-Clustering | Clustering low-resolution galaxy images (WUT) |
mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models
ACL 2026 System Demonstrations — with Jakub Muszyński & Maria Ganzha
Attribution for text–audio multimodal LLMs: modality-aware masking, multi-turn conversation tracking, and phonetic audio grouping.
nlp-shap · MLLM-Shap · Zenodo · DOI · ORCID
Cite@software{pozorski2026mllmshap,
author = {Pozorski, Pawe{\l} Dominik and Muszy{\'n}ski, Jakub Mi{\l}osz and Ganzha, Maria},
title = {mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models},
year = {2026},
publisher = {Zenodo},
doi = {10.5281/zenodo.19678283},
url = {https://zenodo.org/records/19678283}
}| Education | MSc Data Science @ WUT · BSc with honors |
| Built | Botuj — AI chat + voice support |
| Cert | SnowPro Core |
| Based in | Warsaw |
Python PyTorch scikit-learn Transformers FastAPI SQL Snowflake Docker Streamlit
CV project - clustering low-res images, part of IAD at WUT
Jupyter Notebook 2
Repo for Numerical Methods project, part of IAD study program at Faculty of Mathematics and Information Science, Warsaw University of Technology
MATLAB 1
Graphical implementation of A* path finding algorithm
Python
| Back | FazBrowse Home | New Git URL |