Arena Combines Preference and Rubric Rewards to Post-Train FLUX.2-dev

Arena details a post-training method for text-to-image models that combines a reward model trained on 5 million human preference votes with VLM-generated rubric rewards. The approach boosted FLUX.2-dev by 69 Elo, ranking second on the T2I leaderboard.

2026-10-02 ~ 2026-10-03 · 3 related posts

1 near-duplicate retellings: infwinston