HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels
Paper • 2507.21809 • Published • 141
vision
-
-
OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
Paper • 2507.06165 • Published • 60 -
DINOv3
Paper • 2508.10104 • Published • 300 -
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 273 -
Visual-CoG: Stage-Aware Reinforcement Learning with Chain of Guidance for Text-to-Image Generation
Paper • 2508.18032 • Published • 41 -
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
Paper • 2410.10629 • Published • 12 -
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
Paper • 2502.03444 • Published -
Seedream 3.0 Technical Report
Paper • 2504.11346 • Published • 70 -
DanceGRPO: Unleashing GRPO on Visual Generation
Paper • 2505.07818 • Published • 32 -
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
Paper • 2509.06818 • Published • 29 -
Instruct-Imagen: Image Generation with Multi-modal Instruction
Paper • 2401.01952 • Published • 31 -
Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
Paper • 2510.08532 • Published • 6 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 170