Ph.D. Student @ HKUST

Hi, I'm Yaoyang Liu

Making video generation faster

I’m a second-year Ph.D. student at HKUST, advised by Prof. Long Chen. My research focuses on video generation and interactive world models, aiming to make them faster, better, and more controllable.

  • šŸŽ¬ Video Generation
  • šŸŒ Interactive World Models
  • ⚔ Efficient Generation
  • šŸŽ›ļø Controllable Generation

šŸ“° News

  • 2026.10 šŸš€RAR is out on arXiv — one interactive world model, any rollout rate.
  • 2026.05 ⚔SwiftI2V is out — 2K image-to-video generation on a single RTX 4090.
  • 2026.04 šŸŽ‰BA-Att is accepted to CVPR 2026 Findings.
  • 2026.01 šŸŽ‰V2P-Bench is accepted to ICLR 2026.
  • 2025.09 šŸŽ“Started my Ph.D. at HKUST, advised by Prof. Long Chen.
  • 2025.06 šŸŽ‰Magic Mirror is accepted to ICCV 2025.
  • 2024.09 ✨ChronoMagic-Bench is accepted to NeurIPS 2024 D&B Track as a Spotlight.

šŸ“ Selected PublicationsAll publications

RAR: Rate-Adaptive Rollout for Time-Consistent Interactive World Models

Yaoyang Liu*, Dongyu Yan*, Yihua Du, Shengju Qian, Zeke Xie, Xin Wang, Ying-Cong Chen, Long Chen

New Preprint 2026

One interactive world model, any rollout rate. Stride-RoPE places frames sampled at different rates on a shared physical-time axis, enabling consistent multi-rate rollout, unseen-rate generalization, and online rate switching without resetting history.

SwiftI2V: Efficient High-Resolution Image-to-Video Generation via Conditional Segment-wise Generation

Yaoyang Liu, Yuechen Zhang, Wenbo Li, Yufei Zhao, Rui Liu, Long Chen

Preprint 2026

We propose SwiftI2V, an efficient framework for high-resolution (2K) I2V generation that decouples motion modeling from detail synthesis via progressive segment-wise generation and bidirectional contextual interaction. SwiftI2V achieves performance comparable to end-to-end baselines while reducing total GPU-time by 202Ɨ, enabling practical 2K I2V on a single RTX 4090.

šŸŽ“ EducationFull CV

  • The Hong Kong University of Science and Technology (HKUST) 2025.09 – Present
    Ph.D. in Computer Science and Engineering Hong Kong, China

    Advised by Prof. Long Chen.

  • University of Science and Technology of China (USTC) 2021.09 – 2025.06
    B.Eng. in Artificial Intelligence Hefei, China