New interactive world models ActWorld and DreamX-World unveiled
ByPulseAugur Editorial·[6 sources]·
Researchers have introduced two new interactive world models: ActWorld and DreamX-World 1.0. ActWorld enhances navigation-centric models by enabling object interaction through an action-aware memory system and a large dataset of human-object interactions. DreamX-World 1.0 is a general-purpose model capable of long-horizon content generation with camera control and scene persistence, utilizing a specialized data engine and optimization techniques for photorealistic and game-style domains.
AI
IMPACT
These models advance the capabilities of interactive AI environments, potentially impacting training for agents and virtual world simulations.
RANK_REASON
The cluster contains two research papers detailing new interactive world models.
ActWorld extends navigation-centric interactive world models to support object interaction through a chunk-autoregressive framework with hierarchical action-aware memory and persistent memory banks.
DreamX-World 1.0 is a interactive text/image-to-video model that generates long-horizon content with camera control and scene persistence using specialized encoding, training techniques, and optimization methods.
arXiv:2606.17730v1 Announce Type: new Abstract: Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while…
Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pi…
arXiv:2606.16993v1 Announce Type: new Abstract: DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photore…
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon generation. It supports camera navigation, revisits to previously observed regions, and promptable events across photorealistic, game-style, and stylized domains. Our d…