Meta Muse Image Uses RL and Test-Time Compute

AIatMeta · x · 2026-07-08

Meta shares research updates on its image generation model, Muse Image: driven by reinforcement learning, the model "thinks" before generating. By utilizing test-time compute, it achieves predictable near log-linear Elo gains based on the total text and visual tokens. Meta notes that the scalability of this deliberate reasoning and tool calling significantly outperforms standard Best-of-N sampling.

Related event: Meta Launches Muse Image and Muse Video Models(71 posts)→

Original post →

More from Multimodal

Multimodal channel →