Author

Alibaba Group

h-index 7 View on Semantic Scholar

We have 2 of 24 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

CompAdapt: Adaptable Composite Motion Modeling for Physics-Consistent Text-to-Video Generation

While diffusion-based text-to-video (T2V) models have demonstrated impressive capability in generating realistic and temporally coherent videos, they often fail to respect fundamental physical dynamics. Although recent physics-constrained methods incorporate explicit dynamics priors to improve physical plausibility, th...

Hao-Ran Qin, Ren-Rong Wu, Tian-Yu Huang et al. · 0 citations

Towards Streaming Referring Video Segmentation via Large Language Model

This paper proposes a simple but efficient MLLM-based framework StreamingRVOS, which can extend image-level segmentation to video-level via a streaming pipeline without introducing extra parameters and achieves excellent performance in referring video segmentation.

Wenkang Zhang, Kaicheng Yang, Xiang An et al. · 0 citations