Hangoo Kang @ COLM 2026(@hangoo_kang):Really excited to finally share ThunderSyncRL ⚡, a project I co-led with @seilk_! We show that synchronous agentic RL can be up to 1.9× faster without sacrificing on-policy updates, simply by overlapping gradient computation with rollouts. Huge thanks to @Azaliamirh and the entire team!

Hangoo Kang @ COLM 2026

@hangoo_kang

MSCS @StanfordAILab | AI research @ Scaling Intelligence Lab with @Azaliamirh Previously @siebelschool @uiuc_focal_lab

参加 January 2024

171 フォロー中 510 ファン

Hangoo Kang @ COLM 2026@hangoo_kang

2026.10.08 05:32

Really excited to finally share ThunderSyncRL ⚡, a project I co-led with @seilk_! We show that synchronous agentic RL can be up to 1.9× faster without sacrificing on-policy updates, simply by overlapping gradient computation with rollouts. Huge thanks to @Azaliamirh and the entire team!