GitHub
beyond-the-mirror
Field research exposing how LLM safeguards collapse under polite, persistent interaction. Includes full report, metrics, session logs, and the AION conditioning protocol.
indian-legal-document-analyzer
A RAG-based question-answering system for legal documents
penmlab.github.io
Polymer Energy & Materials Lab — Advanced research on functional polymers, Materials, and Energy applications.
emotion-aware-nlp-leveraging-deep-learning-for-contextual-sentiment-understanding
2022-03-03-ucsb-rstudio-reproducibility
This is the repo for the Reproducibility in RStudio workshop
https://github.com/deepset-ai/haystack-evaluation
Using Haystack to benchmark different architectures over different datasets
gemelos-digitales-leyes-de-crecimiento-exponencial-fernandez21212153-
Practica 1: Leyes de crecimiento exponencial
https://github.com/deepset-ai/rag-with-nvidia-nims
🚀 Use NVIDIA NIMs with Haystack pipelines
blockworld-repairs
Repository for the EMNLP'24 paper "Repairs in a Block World: A New Benchmark for Handling User Corrections with Multi-Modal Language Models". Chiyah-Garcia et al. https://arxiv.org/abs/2409.14247
neetbox
[Beta] 🚀 NEETBOX provides the visualization and tooling needed for machine learning experimentation.
https://github.com/gagolews/analiza_danych_w_jezyku_python
M. Gągolewski, M. Bartoszuk, A. Cena, Przetwarzanie i analiza danych w języku Python, PWN, 2016
pysb-units
PySB add-on providing utilities to add units to models and perform dimensional analysis.
parent-lookup
Python package enabling a child object to dynamically lookup its parent at runtime. This allows bidirectional parent-child relationships without hard-coded circular dependencies or circular imports.
intake_catalogues
Intake catalogues for the EERIE data held at the analysis facilities (JASMIN and DKRZ)
illuminator
The Illuminator is an easy-to-use Energy System Integration Development kit to demystify energy system operation, illustrate challenges that arise due to the energy transition and test state-of-the-art energy management concepts.
https://github.com/gagolews/clustering-data-v0
Datasets for Clustering [DEPRECATED – A NEW VERSION IS AVAILABLE]
daisy
Data Information System (DAISY) is a data bookkeeping application designed to help Biomedical Research institutions with their GDPR compliance.
nf-uno
metagenomics pipeline supporting The UnO Project for identifying pathogens in common across outbreak samples
https://github.com/gagolews/bfpm_critique
A Critique of the Bounded Fuzzy Possibilistic Method - Supplementary Files
cheetah-demos
Demos of Cheetah being used for various applications presented in "Cheetah: Bridging the Gap Between Machine Learning and Particle Accelerator Physics with High-Speed, Differentiable Simulations"
ndarray-vector-float32
Create a single-precision floating-point vector (i.e., a one-dimensional ndarray).
laboratoire-didactique
Tools for French-language secondary-school mathematics classes, to practise solving equations
streetscapes
Streetscapes is a package for code for downloading, segmenting and analysing street view images.
https://github.com/gagolews/clustering-data-v1
A framework for benchmarking clustering algorithms – Benchmark suite, version 1
subaligner
Automatically synchronize and translate subtitles, or create new ones by transcribing, using pre-trained DNNs, Forced Alignments and Transformers. https://subaligner.readthedocs.io/
reproducible-publications-quarto
Introduction to Reproducible Publications with Quarto
tiktok-content-scraper
TikTok Content Scraper -- No API-Key needed, minimal dependencies, citable | Download videos (MP4), slides (JPEG) and metadata of author, music, file, hashtags, content, interactions etc.
saits
The official PyTorch implementation of the paper "SAITS: Self-Attention-based Imputation for Time Series". A fast and state-of-the-art (SOTA) deep-learning neural network model for efficient time-series imputation (impute multivariate incomplete time series containing NaN missing data/values with machine learning). https://arxiv.org/abs/2202.08516
lang-luo
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Luo (Kenya and Tanzania) language
texiv
A machine learning–based package for transforming text into instrumental variables (IV).
lang-liv
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Liv language
lang-mya
Finite state and Constraint Grammar based language resources for the Burmese language. Part of the DIGHT 390R course at BYU.
lang-ess
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Central Siberian Yupik language
lang-sel
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Selkup language
lang-vot
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Votic language
lang-ckt
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Chukot language
lang-tqb
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Tembé language
lang-cor
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Cornish language
lang-rup
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Macedo-Romanian/Aromanian language
lang-sju-x-sydlapsk
Finite state and Constraint Grammar based analysers and language resources for the 18th century Southern Saami language.
lang-amh
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Amharic language
https://github.com/gahjelle/vlbi_demo
A simple demonstration of how to run a VLBI analysis
lang-fit
Finite state and Constraint Grammar based analysers and proofing tools, and language resources for the Meänkieli (Tornedalen Finnish) language