🌱 Reconstruct genetic regulation timelines in _Arabidopsis thaliana_ using causal inference, addressing missing data and parameter selection challenges effectively.

Implementation for the NeurIPS 2025 paper: An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Internal Causal Mechanisms Robustly Predict Language Model Out-of-Distribution Behaviors

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Remission af type 2 diabetes med kost og motion

PHP Image Processing

Causal inference of post-transcriptional regulation timelines from long-read sequencing in Arabidopsis thaliana

Stanford NLP Python library for understanding and improving PyTorch models via interventions

Generate avatars with initials from user names.

Image manipulation library

Laravel Integration for Intervention Image

Episimmer is an Epidemic Simulation Framework for Decision Support. It is a highly flexible system that can be easily configured to help take decisions during an epidemic in closed communities like university campuses and gated communities.

Reproducible codebase for my thesis on the Minds@Work-QWL (ADHD) intervention trial using linear mixed-effects modeling.

Stanford NLP Python library for benchmarking the utility of LLM interpretability methods

Symfony Integration for Intervention Image

This is the Github repository for the preprint https://arxiv.org/abs/2505.19612

Wrapper for PHP's GD Library for easy image manipulation. Support for scaling multi-line text, shapes, filters and smart resize.

This project explores methods to detect and mitigate jailbreak behaviors in Large Language Models (LLMs). By analyzing activation patterns—particularly in deeper layers—we identify distinct differences between compliant and non-compliant responses to uncover a jailbreak "direction." Using this insight, we develop intervention strategies that modify

🌄 📐 A Laravel Nova advanced image field with cropping and resizing using Vue Advanced Cropper and Intervention Image

Heart Disease Prediction Using Machine Learning is a logistic regression model that predicts heart disease based on medical data. It analyzes features like age and cholesterol, achieving 85.24% training accuracy and 80.49% testing accuracy, facilitating early detection for timely intervention.