6 papers
Policy-as-Data: Learning Generalizable HOI Diffusion Models from Simulated Physics
Shujia Li, Jianshu Hu, Haiyu Zhang +5
Synthesizing realistic Human-Object Interactions (HOI) is critical for creating embodied avatars and functional virtual environments. However, current data-driven approaches primar…
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Wenqiang Sun, Haiyu Zhang, Haoyuan Wang +7
This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off be…
VDOT: Efficient Unified Video Creation via Optimal Transport Distillation
Yutong Wang, Haiyu Zhang, Tianfan Xue +4
The rapid development of generative models has significantly advanced image and video applications. Among these, video creation, aimed at generating videos under various conditions…
GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects
Shujia Li, Haiyu Zhang, Xinyuan Chen +2
While diffusion models and large-scale motion datasets have advanced text-driven human motion synthesis, extending these advances to 4D human-object interaction (HOI) remains chall…
Weakly Supervised Temporal Sentence Grounding via Positive Sample Mining
Lu Dong, Haiyu Zhang, Hongjie Zhang +5
The task of weakly supervised temporal sentence grounding (WSTSG) aims to detect temporal intervals corresponding to a language description from untrimmed videos with only video-le…
AccVideo: Accelerating Video Diffusion Model with Synthetic Dataset
Haiyu Zhang, Xinyuan Chen, Yaohui Wang +3
Diffusion models have achieved remarkable progress in the field of video generation. However, their iterative denoising nature requires a large number of inference steps to generat…