Noam Ghenassia

Steered Not Stirred: Effective Reward Tilting using Surrogate Reward Mixing

Continuous-time generative models, from diffusion models, flow matching, and now flow maps, owe their practical value to high-fidelity generation and steerability. In many applications, a ground-truth latent ``oracle''reward $R^*$ is unavailable or expensive to evaluate, e.g., human judgments or experimental measuremen...