AI RESEARCH
From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
arXiv CS.CV
•
ArXi:2603.12648v1 Announce Type: new Group Relative Policy Optimization (GRPO) has emerged as a powerful framework for preference alignment in text-to-image (T2I) flow models. However, we observe that the standard paradigm where evaluating a group of generated samples against a single condition suffers from insufficient exploration of inter-sample relationships, cons