Xun Xiao
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
EchoRL proposes a lightweight module to exploit valuable learning signals from advantage-degenerated rollouts in Reinforcement Learning with Verifiable Rewards (RLVR), significantly improving LLM post-training performance.
Papers
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…