Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a g...
Juan-Xi Tian, Jia-Dong Hou, Bai-Ang Li et al.· 0 citations
Game world models have recently demonstrated promising capabilities in generating visually coherent and action-controllable gameplay videos. However, non-player character (NPC) behavior in existing models is either implicitly entangled with video generation or explicitly prescribed through external control signals. Con...
Zhi-Yang Deng, Bo-Ran Zhang, Dan Chen et al.· 3 citations
Recent game world models support realistic visual simulation and interactive gameplay based on player inputs. However, they typically learn environment dynamics from pixel-level supervision, jointly modeling perception, memory, state transitions, and rendering within a single end-to-end framework. While this design ena...
Zi-Jun Lin, Zhi-Yang Deng, Yu-Zhe Wu et al.· 2 citations
StoryEngine is proposed, a state-grounded agentic framework for video storytelling that maintains a structured representation of entity placement and story-relevant states, and propagates event-induced changes to define the intended start and end states of each shot.
This work examines what structure is supplied by the game or workflow, what AI learns or produces, which capabilities and artifacts transfer across settings and roles, and what evidence supports the claims and identifies cross-role connections.
Meng-Yang-Yu-Jing-Jia Luo, Yan-Lin Li, Hao Li et al.· arXiv.org· 4 citations
Drive-HWM is presented, a hierarchical slow--fast world modeling framework that organizes future representation prediction and action generation at complementary temporal scales and introduces Dynamic-Aware Latents learned through optical-flow prediction.
Zhao-Xin Fan, Tian-Bao Zhang, Wen-Jun Wu et al.· 0 citations
BooM-VVT is proposed, a mask-free VVT framework built upon the keyframe-driven video generation paradigm, and Garment-Sensitive Keyframe Sampling, which selects keyframes based on garment-relevant body regions to better capture garment appearance, is introduced.
Wei Zhang, Xin Li, Pei-Shu Shi et al.· 0 citations
H3-World, an efficient framework that turns the 33B MiniMax-H3 video generator into an interactive world model, and introduces temporal attention routing, which restricts each instruction to its intended time interval and reduces control leakage across actions.
Dan Chen, Ze-Qing Wang, Zibin Lin et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.