A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
MultiGen: Level-design for editable multiplayer worlds in diffusion game engines
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5years
2026 5representative citing papers
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
MilliVid compresses video frames into multi-scale token hierarchies and uses coarse-to-fine rollout in a diffusion model to maintain long-range geometric and object consistency on Minecraft videos.
This survey reviews trends, challenges, benchmarks, and future directions in action-conditioned interactive world modeling for video and 3D generation.
citing papers explorer
-
Multiplayer Interactive World Models with Representation Autoencoders
A 5B-parameter latent diffusion model generates real-time four-player Rocket League matches conditioned on all players' actions, staying stable far beyond its training horizon.
-
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Per-frame natural-language action prompts enable simultaneous multi-entity control and cross-entity action transfer in interactive video world models, outperforming discrete action-index interfaces.
-
Echo-Memory: A Controlled Study of Memory in Action World Models
A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately measure memory quality.
-
MilliVid: Hierarchical Latents for Long-Range Consistency in Video Generation
MilliVid compresses video frames into multi-scale token hierarchies and uses coarse-to-fine rollout in a diffusion model to maintain long-range geometric and object consistency on Minecraft videos.
-
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
This survey reviews trends, challenges, benchmarks, and future directions in action-conditioned interactive world modeling for video and 3D generation.