Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models Paper • 2508.09968 • Published 22 days ago • 15
Matrix-3D: Omnidirectional Explorable 3D World Generation Paper • 2508.08086 • Published 24 days ago • 70
Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation Paper • 2508.07981 • Published 24 days ago • 58
HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels Paper • 2507.21809 • Published Jul 29 • 124
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling Paper • 2507.07982 • Published Jul 10 • 32
T-LoRA: Single Image Diffusion Model Customization Without Overfitting Paper • 2507.05964 • Published Jul 8 • 116
LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion Paper • 2507.02813 • Published Jul 3 • 60
BlenderFusion: 3D-Grounded Visual Editing and Generative Compositing Paper • 2506.17450 • Published Jun 20 • 63
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition Paper • 2506.17201 • Published Jun 20 • 55