Shinnosuke ONO / 小野新之介 ✈️ ICML2026 🇰🇷 (@shinnosukeono) “We present our paper "Mitigating Reward Hacking via Adversarial Robustness" at E” — TopicDigg
Shinnosuke ONO / 小野新之介 ✈️ ICML2026 🇰🇷
@shinnosukeono
Machine Learning Master's student at @UTokyo_News_en. Staying at @NTUSg from Jul-Dec '26. Intern at EQUES, @Matsuo_Lab. Prev: @MatsuoInstitute, IS23er.
加入 April 2025
74 正在关注 39 粉丝
We present our paper "Mitigating Reward Hacking via Adversarial Robustness" at EIML@ICML2026!
We conjecture that reward hacking is often caused by flipped advantage-sign estimations, and propose SignCert-PO, a new algorithm built on the theory of randomized smoothing! 🧵
显示更多
