World Model

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Abstract: The field of 4D world modeling - aiming to jointly capture spatial geometry and temporal dynamics - has witnessed remarkable progress in recent years, driven by advances in large-scale generative models and multimodal learning.
... (other authors), Haoyi Zhu 朱皓怡, ... (19 authors)
Cite Website arXiv GitHub
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
DeepVerse: 4D Autoregressive Video Generation as a World Model
Abstract: World models serve as essential building blocks toward Artificial General Intelligence (AGI), enabling intelligent agents to predict future states and plan actions by simulating complex physical interactions. However, existing interactive models primarily predict visual observations, thereby neglecting crucial hidden states like geometric structures and spatial coherence.
Junyi Chen, Haoyi Zhu 朱皓怡, Xianglong He, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Yang Zhou, Zizun Li, Zhoujie Fu, Jiangmiao Pang, Tong He
Cite Website GitHub PDF arXiv
DeepVerse: 4D Autoregressive Video Generation as a World Model
Aether: Geometric-Aware Unified World Modeling
A geometric-aware unified world model, capable of 4D reconstruction, action-conditioned prediction, and visual planning.
Haoyi Zhu 朱皓怡, Yifan Wang, Jianjun Zhou, Wenzheng Chang, Yang Zhou, Zizun Li, Junyi Chen, Chunhua Shen, Jiangmiao Pang, Tong He
Cite Project PDF arXiv Code
Aether: Geometric-Aware Unified World Modeling