9h ago

MIRO Introduces Multi-Reward Training for Aligned Text-to-Image Models

0
Original post

Excited to share that MIRO is accepted to ICML 2026 @icmlconf ! 🎉 We introduce multi-reward conditioned training for text-to-image. By training on continuous reward scores, we can simply condition on HIGH REWARDS at inference to guarantee top-tier, aligned outputs.

7:35 AM · May 20, 2026 View on X