arxiv:2606.10747
Lukas Galke Poech
lgalke
AI & ML interests
LLM interpretability, agentic/multi-agent safety
Recent Activity
authored a paper 3 days ago
The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent Misalignment authored a paper 8 days ago
BrainSurgery: Reproducible and Reliable Declarative Weight Manipulations for Model Editing and UpcyclingOrganizations
arxiv:2606.09707
arxiv:2606.06286
arxiv:2605.31170
arxiv:2605.26045
arxiv:2605.07462
arxiv:2512.07407
arxiv:2603.12117
arxiv:2602.08818
arxiv:2512.04799
arxiv:2508.02271
arxiv:2505.14524
arxiv:2502.11895
arxiv:2502.06728
arxiv:2412.08528
arxiv:2411.05882
arxiv:2311.09707
arxiv:2302.12239
arxiv:2204.03954
arxiv:1902.06423
