Ahmad Beirami @ ICLR 2025 (@abeirami) 's Twitter Profile
Ahmad Beirami @ ICLR 2025

@abeirami

Generative AI post-training @GoogleDeepMind/@GoogleResearch | ex-{@AIatMeta, @EA, @MIT, @Harvard, @DukeU} | @GeorgiaTech PhD | زن زندگی آزادی | opinions my own

ID: 1073974163704958976

linkhttp://www.mit.edu/~beirami/ calendar_today15-12-2018 16:12:48

2,2K Tweet

6,6K Followers

2,2K Following

Ahmad Beirami @ ICLR 2025 (@abeirami) 's Twitter Profile Photo
Ahmad Beirami @ ICLR 2025
@abeirami

6 months ago

𝐛𝐞𝐬𝐭-𝐨𝐟-𝐧 is a strong baseline for - improving agents - scaling inference-time compute - preference alignment - jailbreaking models How does 𝐁𝐨𝐧 work? and why is it so strong? Find some answers in the paper we wrote over two Christmas breaks!🧵

𝐛𝐞𝐬𝐭-𝐨𝐟-𝐧 is a strong baseline for - improving agents - scaling inference-time compute - preference alignment - jailbreaking models How does 𝐁𝐨𝐧 work? and why is it so strong? Find some answers in the paper we wrote over two Christmas breaks!🧵