5 papers
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
Siming Fu, Haojun Xu, Ruizhe He +9
Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfull…
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Siming Fu, Zheming Fu, Ruizhe He +7
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, match…
FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
Zheming Fu, Ruizhe He, Wei Shang +4
Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing density-approximated policy gr…
Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
Xiaoxuan He, Siming Fu, Zeyue Xue +9
Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14…
HPSv3++: Scaling Reward Models Across the Full Spectrum of Diffusion Model Capabilities
Yijun Liu, Jie Huang, Zeyue Xue +5
Reward models guide text-to-image (T2I) systems toward outputs aligned with human preferences. However, typical reward models such as HPSv3 are trained on pre-annotated data from e…