Lukas Galke Poech

lgalke

·

https://lgalke.github.io

AI & ML interests

LLM interpretability, agentic/multi-agent safety

Recent Activity

updated a model 3 days ago

danish-foundation-models/DFM-Mimir

liked a model about 1 month ago

danish-foundation-models/DFM-Mimir

upvoted a paper about 1 month ago

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

View all activity

Organizations

Papers 20

arxiv:2606.10747

arxiv:2606.09707

arxiv:2606.06286

arxiv:2605.31170

models 1

lgalke/Qwen3.5-35B-A3B-psysafe

Image-Text-to-Text • 36B • Updated Mar 25 • 3

datasets 0

None public yet