Zixiang Gao

2 accepted papers

2026

DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation

Jie Hu, Zixiang Gao, Yutong He, Kun Yuan

ICML 2026poster

Diffusion transformers have achieved remarkable success in high-quality video generation, yet their reliance on spatiotemporal 3D full attention incurs prohibitive computational cost due to the quadratic complexity of attention. Block sparse attention is a common approach to mitigate this by focusin…

Cited by 2 Source ↗Scholar ↗

2025

ROSE: Remove Objects with Side Effects in Videos

Chenxuan Miao, Yutong Feng, Jianshu Zeng, Zixiang Gao, Liu Hantang, Yunfeng Yan +4

NeurIPS 2025poster

Video object removal has achieved advanced performance due to the recent success of video generative models. However, when addressing the side effects of objects, \textit{e.g.,} their shadows and reflections, existing works struggle to eliminate these effects for the scarcity of paired video data as…

Cited by 0 Source ↗Scholar ↗