Sophia Wiedmann

Identifiers

• name variant Sophia Wiedmann 0.60 · backfill

Papers (1)

1. MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward Optimization cs.AI · 2026 · author #4

Mentions

• 2605.29951 #4 · arxiv_oai · confidence 0.70 Sophia Wiedmann

Frequent Coauthors

• Anisha Saha 1 shared papers
• Teodora Kamova 1 shared papers
• Timothy Hospedales 1 shared papers
• Varsha Suresh 1 shared papers
• Vera Demberg 1 shared papers