Showing 2026Show all
2 papers · 1 filter
cs.CV2026
SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO
Yunkai Yang, Yudong Zhang, Xinying Chen +5
Reinforcement Learning (RL) has proven effective in aligning flow-based generative models with human preferences. Recently, Flow-GRPO has emerged as an efficient critic-free paradi…
cs.CV2026
ControlRef: Efficient Layout-Guided Multi-Instance Generation via Anchored 4D-RoPE
Yunkai Yang, Yudong Zhang, Xinying Chen +7
Layout-guided multi-instance generation is essential for controllable image synthesis in Multi-Modal Diffusion Transformers (MM-DiTs). However, integrating this capability into uni…