Hugging Face's logo
Lukas Galke Poech's picture

Lukas Galke Poech

lgalke
13 24
giannor's profile picture williambrach's profile picture EvilScript's profile picture
·
https://lgalke.github.io

AI & ML interests

LLM interpretability, agentic/multi-agent safety

Recent Activity

authored a paper 1 day ago
Selecting The Most Informative Tokens in Natural Language Autoencoders
authored a paper 1 day ago
Write Once, Run Everywhere: The Axon DSL for Shape-Safe and Framework-Agnostic LLM Architectures
authored a paper 1 day ago
DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data
View all activity

Organizations

MLX Community's profile picture Danish Foundation Models's profile picture Schneider-Kamp Lab's profile picture Machine Ecology Lab's profile picture Inversion Lab for AI Safety's profile picture RUNE Lab's profile picture filter with espresso's profile picture AI Safety & Interpretability Lab's profile picture