Kaan Ozkara

Identifiers

• name variant Kaan Ozkara 0.60 · backfill

Papers (1)

1. Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models cs.LG · 2026 · author #3

Mentions

• 2605.25189 #3 · arxiv_oai · confidence 0.70 Kaan Ozkara

Frequent Coauthors

• Christos Thrampoulidis 1 shared papers
• Jiaji Huang 1 shared papers
• Wenlong Deng 1 shared papers
• Xiaoxiao Li 1 shared papers
• Youngsuk Park 1 shared papers
• Yushu Li 1 shared papers