L3G-World Real-time Infinite World Generation Model Released
The story so far
qwen has released the L3G-World model, used for real-time generation of spatially consistent interactive worlds. The model uses compact latent 3D Gaussian memory and video diffusion Transformer to alternately perform autoregressive updates. By generating Gaussians in new areas and refining existing Gaussians, L3G-World's memory grows with the scope of the scene rather than the length of the flow, with each Gaussian storing VAE latent features that can be directly rendered into DiT's latent space.
AI-written from the reports · Updated 20 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersL3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory
L3G-World uses compact latent 3D Gaussian memory and video diffusion Transformers to alternately perform autoregressive updates, generating spatially consistent interactive worlds in real time. The model grows memory with the scene range rather than the flow length by generating Gaussians in new areas and refining existing Gaussians, each storing VAE latent features that can be directly rendered into DiT's latent space.