CoRe: Co-Evolving Reward Models for Mitigating Latent Reward Hacking in Video Diffusion Models

arXiv cs.AISeptember 30, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.36245v1 Announce Type: new Abstract: Latent reward models (LRMs) enable efficient alignment of video diffusion models by scoring intermediate states directly in latent space. However, we find that optimizing against a fixed latent reward rapidly leads to latent reward hacking: the predicted reward stays high while perceptual and motion quality deteriorate. Our analysis identifies distributional escape as the central cause: within a few hundred updates, the generator moves beyond the reward model's training support, where its scores no longer reflect video quality. Based on this insight, we introduce CoRe, a co-evolving reward framework that treats latent-space alignment as a dynam

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Verktyg
• Forskning
• Bild