Ziqi Huang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Vision×1AI×1
Frequent co-authors
Research Timeline
2026
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
This paper introduces UMM-Reflection, a reinforcement learning approach to improve image generation by learning to revise and reflect on its own generations.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIEmpiricalRecentSep 28, 2026
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li +4 more
This paper introduces UMM-Reflection, a reinforcement learning approach to improve image generation by learning to revise and reflect on its own generations.
View →