People | OdenseNLP

Peter Schneider-Kamp

Full Professor | Group Leader

Language Modeling Efficient ML

Lukas Galke Poech

Associate Professor | Group Leader

My research advances AI safety by investigating how and why advanced AI systems behave the way they do. Website

Language Modeling Interpretability Multi-agent Safety

Gianluca Barmina

PhD Fellow

I primarily work on LLMs evaluation and interpretability, currently with a focus on representational engineering of LLMs. I’m also i...

Evaluation AI Safety Interpretability LLMs + KGs

Jacob Nielsen

PhD Fellow

I primarily work with efficient deep learning in all aspects from training to inference. I am interested in many aspects and keep ge...

Language Modelling Efficient and Dederated Deep Neural Network Architectures Efficient Distributed Trainings Extreme Quantization

Filippo Tonini

PhD Fellow

I work with LLM agents safety in multi-agent simulations, I love climbing, nature and ethical research.

AI Safety Natural Language Processing Machine Learning

Stine Lyngsø Beltoft

PhD Fellow

I’m a PhD student in data science, working on how artificial intelligence can engage with human perspectives, values, and ambiguity....

Digital Humanities Computational Social Science AI4Science

Andrea Blasi Núñez

PhD Fellow

My work sits at the intersection of AI and healthcare — applying Language Models to real clinical problems and making sure they perf...

Large Language Models Applications in healthcare

Annemette Brok Pirchert

PhD Fellow

I work on developing and understanding flexible multilingual language models. My research spans model development, mechanistic inter...

Multilingual Language Models Efficient and Flexible Language Models Mechanistic Interpretability AI Safety

Federico Torrielli

Guest Researcher, PhD Fellow

I work primarily on AI safety. My main research interests include AI alignment, human-GenAI interaction, and mechanistic interpretab...

AI Safety Mechanistic Interpretability Human-AI Interaction

Jonas Vistrup

Former PhD Fellow

I work with creating explainable and transparent AI systems for law by applying traditional AI methods in collaboration with Large L...

Symbolic AI Hybrid AI Legal AI

Anton D. Lautrup

PostDoc

I work with generative models and machine learning, usually trying to simplify things, improve evaluation etc.

Generative Models Mechanistic Interpretability Machine Learning

Danial Namazifard

PhD Fellow

My research focuses on interpretability, natural language processing, and AI safety, with a particular interest in understanding how...

Interpretability Natural Language Processing AI Safety

William Brach

Latent Collaborator

Language Modeling Information extraction Multi-agent collaboration

Anna Schneider-Kamp

Associate Professor

HAnna Schneider-Kamp is an Associate Professor of Health and Consumption. Her main research interest is the empirical study and theo...

Qualitative methods Human-centered AI Digital humanities