Belen Martin Urcelay

Identifiers

• name variant Belen Martin Urcelay 0.60 · backfill

Papers (1)

1. Preference Instability in Reward Models: Detection and Mitigation via Sparse Autoencoders cs.LG · 2026 · author #3

Mentions

• 2605.16339 #3 · arxiv_oai · confidence 0.70 Belen Martin Urcelay

Frequent Coauthors

• Francesco Croce 1 shared papers
• Shunchang Liu 1 shared papers
• Xin Chen 1 shared papers