2 papers
cs.CV2026
Faster and Better Alignment for Flow Matching Models via Step-aware Advantages
Zhixiong Yue, Zixuan Ni, Feiyang Ye +4
Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few-step text-to-image generators.…
cs.CV2025
FPGA: Flexible Portrait Generation Approach
Zhaoli Deng, Fanyi Wang, Junkang Zhang +5
Portrait Fidelity Generation is a prominent research area in generative models.Current methods face challenges in generating full-body images with low-resolution faces, especially…