Magnus J{\o}rgenv{\aa}g

Identifiers

• name variant Magnus J{\o}rgenv{\aa}g 0.60 · backfill

Papers (2)

1. Reinforcement Learning Amplifies Emergent Misalignment from Harmless Rewards cs.CL · 2026 · author #1
2. In-Training Defenses against Emergent Misalignment in Language Models cs.LG · 2025 · author #2

Mentions

• 2508.06249 #2 · arxiv_oai · confidence 0.70 Magnus J{\o}rgenv{\aa}g
• 2605.31328 #1 · arxiv_oai · confidence 0.70 Magnus J{\o}rgenv{\aa}g

Frequent Coauthors

• David Kacz\'er 2 shared papers
• Florian Mai 2 shared papers
• Lucie Flek 2 shared papers
• Clemens Vetter 1 shared papers
• Esha Afzal 1 shared papers
• Lasse Ruttert 1 shared papers
• Marvin G\"ulhan 1 shared papers
• Robin Haselhorst 1 shared papers