9 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…
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…
World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
Weijie Wang, Xiaoxuan He, Youping Gu +9
Recent video foundation models demonstrate impressive visual synthesis but frequently suffer from geometric inconsistencies. While existing methods attempt to inject 3D priors via…
A Systematic Post-Train Framework for Video Generation
Zeyue Xue, Siming Fu, Jie Huang +9
While large-scale video diffusion models have demonstrated impressive capabilities in generating high-resolution and semantically rich content, a significant gap remains between th…
SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human Feedback
Xiaoxuan He, Siming Fu, Wanli Li +5
Aligning diffusion models with human preferences remains challenging, particularly when reward models are unavailable or impractical to obtain, and collecting large-scale preferenc…
TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
Xiaoxuan He, Siming Fu, Yuke Zhao +5
Recent flow matching models for text-to-image generation have achieved remarkable quality, yet their integration with reinforcement learning for human preference alignment remains…
R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization
Yi Yang, Xiaoxuan He, Hongkun Pan +9
Large Language Models have demonstrated remarkable reasoning capability in complex textual tasks. However, multimodal reasoning, which requires integrating visual and textual infor…
Towards Calibrated Hyper-Sphere Representation via Distribution Overlap Coefficient for Long-tailed Learning
Hualiang Wang, Siming Fu, Xiaoxuan He +3
Long-tailed learning aims to tackle the crucial challenge that head classes dominate the training procedure under severe class imbalance in real-world scenarios. However, little at…