AI RESEARCH
AR-CoPO: Align Autoregressive Video Generation with Contrastive Policy Optimization
arXiv CS.CV
•
ArXi:2603.17461v1 Announce Type: new Streaming autoregressive (AR) video generators combined with few-step distillation achieve low-latency, high-quality synthesis, yet remain difficult to align via reinforcement learning from human feedback (RLHF). Existing SDE-based GRPO methods face challenges in this setting: few-step ODEs and consistency model samplers deviate from standard flow-matching ODEs, and their short, low-stochasticity trajectories are highly sensitive to initialization noise, rendering intermediate SDE exploration ineffective.