Arena's 5M-vote post-training lifts FLUX.2-dev to #2 on live T2I leaderboard

infwinston · x · 2026-10-03

Arena shares a post-training recipe for text-to-image models that combines human preference signals with explicit rubric-based rewards.

Related event: Arena Combines Preference and Rubric Rewards to Post-Train FLUX.2-dev(3 posts)→

Original post →

More from Multimodal

Multimodal channel →