PixVerse R2
Summary
PixVerse R2 is a real-time world model that generates continuously evolving audiovisual worlds, accepting text, images, audio, and actions with session memory for interactive and controllable experiences.
View Cached Full Text
Cached at: 09/25/26, 11:13 AM
Similar Articles
@yifanzhang_: Very interesting model architecture that uses block-sparse attention. https://pixverse.ai/en/blog/pixverse-r2-scaling-r…
PixVerse R2 introduces a unified scaling architecture for real-time audiovisual world models, leveraging block-sparse attention and continuous pretraining to enhance video generation and interactive control.
DreamX-World 1.0: A General-Purpose Interactive World Model
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model that supports camera navigation, scene persistence, and promptable events across multiple domains, using novel techniques like E-PRoPE, causal forcing, and memory-conditioned scene persistence to achieve controllable long-horizon generation.
WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon
WorldPlay2 is an interactive world model that integrates a factorized hybrid control interface with compressed memory and stable distillation to enable real-time responsiveness and long-horizon consistency in control tasks.
PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space
PixWorld presents a unified pixel-space diffusion approach for 3D scene reconstruction and generation, overcoming limitations of latent-space methods by using direct image-level supervision and geometry-aware feature alignment. The method outperforms prior generation methods and matches state-of-the-art reconstruction methods.
Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation
Vidu S2 presents real-time interactive AI models for avatar and video editing, enabling high-resolution spatial video generation with dynamic reference updates and superior performance over baselines.