04:00
2026-08-05
arxiv.org
artificial-intelligence
Crayotter: Learning Long-Horizon Video Editing Agents via Group-Relative Preference Backpropagation
Researchers introduced Group-Relative Preference Backpropagation (GRPB), a method that converts same-task rankings into zero-sum advantages to train long-horizon video editing agents, and released theβ¦