Ruotong Liao
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
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
TunerDiT introduces a training-free progressive steering method to enhance multi-event video generation using Diffusion Transformers, achieving state-of-the-art performance by explicitly managing event boundaries and cross-event semantics.
Highlighted terms show continued research focus across papers
Papers
cs.CVcs.AIRecentMay 29, 2026
TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation
Ruotong Liao, Guowen Huang, Qing Cheng, Guangyao Zhai +5 more
TunerDiT introduces a training-free progressive steering method to enhance multi-event video generation using Diffusion Transformers, achieving state-of-the-art performance by explicitly managing even…
View →