6 papers
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation
Jeffrey Hu, Daniel Olmeda Reino, Ayush Tewari
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-distribution data from procedural generators, continue to viola…
Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update
Sitian Shen, Jiuming Liu, Mengmeng Liu +7
Recent video world models have witnessed the paradigm shift from single-agent to multi-agent involvements, which can reveal more complicated dynamics and cross-agent interaction in…
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
Jiuming Liu, Chaojun Ni, Mengmeng Liu +7
With rapid development of large language models and diffusion-based content generation, world modeling has attracted increasing research attention, benefiting various downstream do…
How do people watch AI-generated videos of physical scenes?
Danqing Shi, Lan Jiang, Katherine M. Collins +3
The growing prevalence of realistic AI-generated videos on media platforms increasingly blurs the line between fact and fiction, eroding public trust. Understanding how people watc…
Efficient Camera-Controlled Video Generation of Static Scenes via Sparse Diffusion and 3D Rendering
Jieying Chen, Jeffrey Hu, Joan Lasenby +1
Modern video generative models based on diffusion models can produce very realistic clips, but they are computationally inefficient, often requiring minutes of GPU time for just a…
VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation
Felix O'Mahony, Roberto Cipolla, Ayush Tewari
Generative video models, a leading approach to world modelling, face fundamental limitations. They often violate physical and logical rules, lack interactivity, and operate as opaq…