Peter Schneider-Kamp
I like to build efficient deep learning models and, most importantly, I like to have fun :)
I like to build efficient deep learning models and, most importantly, I like to have fun :)
My research advances AI safety by investigating how and why advanced AI systems behave the way they do. Website
I primarily work with efficient deep learning in all aspects from training to inference. I am interested in many aspects and keep ge...
I primarily work on LLMs evaluation and interpretability. I’m also interested in the intersection of LLMs and knowledge graphs, and ...
I work with LLM agents safety in multi-agent simulations, I love climbing, nature and ethical research.
I’m a PhD student in data science, working on how artificial intelligence can engage with human perspectives, values, and ambiguity....
I work on efficient long-context inference for large language models at SubQ, alongside distributed training of large-scale neural n...
My work sits at the intersection of AI and healthcare — applying Language Models to real clinical problems and making sure they perf...
I work on developing and understanding flexible multilingual language models. My research spans model development, mechanistic inter...
My research focuses on interpretability, natural language processing, and AI safety, with a particular interest in understanding how...
I primarily work on language model development and analysis. With a background in mathematics, I am particularly interested in the m...
I work with generative models and machine learning, usually trying to simplify things, improve evaluation etc.
My research centers on machine learning, feature selection, explainability, and evaluation measures and metrics.
I work primarily on AI safety. My main research interests include AI alignment, human-GenAI interaction, and mechanistic interpretab...
I work with creating explainable and transparent AI systems for law by applying traditional AI methods in collaboration with Large L...