Sitemap

Page Not Found

Personal website for LYY

Posts by Category

Posts by Collection

CV

Page Archive

Publications

Sitemap

Posts by Tags

Blog posts

ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

Shenghai Yuan, Jinfa Huang, Yongqi Xu, Yaoyang Liu, Shaofeng Zhang, Yujun Shi, Ruijie Zhu, Xinhua Cheng, Jiebo Luo, Li Yuan

NeurIPS D&B (Spotlight), 2024

ChronoMagic-Bench can reflect the physical prior capacity of Text-to-Video Generation Model.

arXiv Project Code

Magic Mirror: ID-Preserved Video Generation in Video Diffusion Transformers

Yuechen Zhang*, Yaoyang Liu*, Bin Xia, Bohao Peng, Zexin Yan, Eric Lo, Jiaya Jia

ICCV, 2025

MagicMirror is a video generation framework that preserves identity while producing high-quality, natural motion, achieving state-of-the-art results with minimal added parameters.

arXiv Project Code

V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction

Yiming Zhao, Yu Zeng, Yukun Qi, Yaoyang Liu, Lin Chen, Zehui Chen, Xikun Bao, Jie Zhao, Feng Zhao

ICLR, 2026

V2P-Bench is a comprehensive benchmark specifically designed to evaluate the video understanding capabilities of LVLMs in human-model interaction scenarios.

arXiv Project Code

Efficient Long-Context Modeling in Diffusion Language Models via Block Approximate Sparse Attention

Wenhu Zhang, Yiming Wu, Huanyu Wang, Yaoyang Liu, Huanzhang Dou, Senqiao Yang, Sitong Wu, Hanbin Zhao, Jiaya Jia

CVPR Findings 2026

We propose BA-Att, a block approximate sparse attention framework with pre-downsampling and covariance-compensated correction, achieving up to 6.95× speedup over FlashAttention at 50% sparsity across language, multimodal, and video generation models.

arXiv Project Code

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 202×, enabling practical 2K I2V on a single RTX 4090.

arXiv Project Code